List Blueprint doctrine with stable slugs, titles, and clusters. The lens selects which of the three public doctrines: 'architecture' = the 10 agentic principles (default, the architect.validate rubric); 'surface' = the 8 experience-design laws (the design.validate rubric); 'spec' = the 8 spec-quality laws (the spec.validate rubric). Use this when you need the full inventory or want every entry in one cluster (pass cluster slug to filter). Prefer principles.search when the user describes a topic, failure mode, or keyword in natural language. Prefer principles.get when you already know the exact slug and need full detail.

List all principle clusters with their stable slugs and linked principle titles. Use this to discover which clusters exist before drilling in with clusters.get or filtering principles.list by cluster. Prefer clusters.get when you already know the cluster slug and need full detail.

Get one doctrine entry by stable slug. The lens selects the doctrine: 'architecture' = one of the 10 agentic principles (default); 'surface' = one of the 8 experience-design laws; 'spec' = one of the 8 spec-quality laws. Returns id, title, cluster, definition, rationale, implications, and risk-if-violated (laws also carry their eponym and validator_questions). Use this when you already have the exact slug from principles.list; prefer principles.search when the user describes a topic or failure mode in natural language; prefer principles.list when you need every entry or every entry within a cluster. Returns error_payload on unknown slug for the lens.

Get one principle cluster by stable slug. Returns the cluster definition, shared rationale, and the full set of member principles (slug + title) so the caller can pivot into principles.get without a second list call. WHEN TO CALL: the user has already named a specific cluster (e.g. 'delegation', 'visibility', 'trust', 'orchestration') OR you have a slug from a prior clusters.list / principles.list response and need its full definition + member principles. The response embeds member principle slugs + titles already, so DO NOT loop principles.get over each member to get a cluster overview — read the response. WHEN NOT TO CALL: the user is describing a topic, failure mode, or keyword in natural language (call principles.search instead); the user wants to discover which clusters exist (call clusters.list); the user wants the definition of one specific principle (call principles.get directly). Idempotent + cacheable per slug. Returns 404-shaped error_payload on unknown slug — the slug must match exactly the value emitted by clusters.list, with no normalization.

Get one curated example by stable slug. Returns title, summary, source-code links, principle coverage (the principle slugs the example demonstrates), difficulty, library/framework, and implementation notes. Use this when you already have the slug from examples.search, a principles.get response, or a guide cross-link; prefer examples.search when filtering by topic / principle / difficulty / library; prefer guides.get when the caller wants a full walkthrough rather than a single reference example. Returns error_payload on unknown slug.

Search Blueprint principles by free-text query and return the closest matches ranked by relevance. Use this to find principles related to a specific design challenge, failure mode, or keyword (e.g. 'reversibility', 'approval flow', 'delegation boundary'). Returns principle title, cluster, definition, rationale, and implementation heuristics. Prefer this over principles.list when you have a specific topic in mind rather than wanting all principles. NOTE: search currently covers the 10 agentic principles only; for the 8 experience-design laws or the 8 spec-quality laws use principles.list(lens='surface') / principles.list(lens='spec') until search spans all three lenses.

Search curated examples by free-text query, ranked by relevance, with optional filters: principle_ids (only examples covering those principles), difficulty (beginner/intermediate/advanced), library (e.g. 'langgraph', 'openai'). Returns each match's slug, title, summary, principle coverage, difficulty, library, and source-code link — slug is the handle examples.get hydrates. Default limit 5, capped server-side. Use this when the user describes a use case, technique, or library and wants matching examples; prefer examples.get when you already have the slug; prefer guides.search when the user wants a full walkthrough; prefer principles.search when the user wants doctrine guidance, not an implementation.

Public — list downloadable doctrine and agent asset artifacts (skill packs, rule packs, MCP setup snippets) the user can drop into their AI coding tool to import the Blueprint as native skill/rule files. Returns a list of assets with name, format (one of: zip / md / markdown / mdc / json / toml / text — the full vocabulary), pack_version, download_url, and platform target (Claude Code, Cursor, Codex, Gemini, Qwen). The response also carries count (length of assets) for symmetry with principles.list / clusters.list / guides.list. WHEN TO CALL: the user asks how to bring the Blueprint into their coding agent, or wants to install it as a local skill/rule file. WHEN NOT TO CALL: for the live MCP tools themselves — those are already available through this server. For doctrine content, prefer principles.list/get and guides.list/get. BEHAVIOR: read-only, idempotent, no auth required. Asset artefacts are regenerated on every deploy from the canonical doctrine.

List application guides that show how Blueprint principles apply to engineering challenges (security, evaluation, observability, etc.). Use this to discover which guides exist before drilling in. Prefer guides.search when the user describes a topic or failure mode in natural language. Prefer guides.get when you already know the guide slug and need full detail.

Get a full application guide by its stable slug (e.g. 'security-application', 'observable-evaluation'). Returns sections, action items, and linked principles. Use this when you already have the guide slug from guides.list or guides.search. Prefer guides.search when the user describes a topic in natural language; prefer guides.list when you need the full inventory.

Search application guides by free-text query, matched against section answers and action items. Use this when the user describes an engineering challenge (security review, evaluation harness, observability) and wants matching guides. Prefer guides.get when you already have the guide slug; prefer guides.list when you need the full inventory.

Pro/Teams — records a value moment (e.g. review_confidence, runtime_risk_found, workflow_clarity) after a successful validate run on any lens — architect.validate, design.validate, or spec.validate — or a doctrine session. Each event captures event_type, surface_used (mcp/web/cli), perceived_value (1-5), and an optional brief_context — structured fields only, NO prompts or code stored. WHEN TO CALL: after architect.validate, design.validate, or spec.validate returns a clearly useful result AND the user has acknowledged the value (or you ask them "would you rate this 1-5?"). Each validator's response carries an explicit next_step instruction telling the agent to OFFER this call — surface that offer to the user. WHEN NOT TO CALL: silently or without the user's awareness; on every validate (only after a clear value moment); to capture intent or speculative value. If the user declines, do not retry within the same session. BEHAVIOR: write-only, single insert into ValueEvent. Auth: Bearer , Pro or Teams plan required. UK/EU residency. Do NOT include proprietary code, prompt content, or PII in brief_context — it surfaces in admin AI-visibility dashboards. Expect a 1-line acknowledgment in the response; the structured feedback is then aggregated server-side.

Public — records explicit free-text user feedback about the Blueprint, this tool surface, or a specific principle/example. Captures category (bug, doctrine_critique, missing_example, ergonomics, other), free-text body, and optional contact_email when permission_to_follow_up is true. WHEN TO CALL: ONLY when the user explicitly says they want to give feedback (e.g. 'can you log this as feedback', 'file this critique', 'send a bug report'). Use signals.report instead for value-moment metrics (rating validate's output 1-5). WHEN NOT TO CALL: proactively, silently, or to substitute for signals.report. Never harvest contact info without explicit permission_to_follow_up=true. BEHAVIOR: write-only, no auth required (open to all callers), single insert into UserFeedback. UK/EU residency. contact_email is stored ONLY when permission_to_follow_up=true, and that fact is confirmed back in the response so the user can see the privacy boundary.

Pro/Teams — first-pass doctrine review of agentic code/workflow against the 10-principle Agentic AI Blueprint. ON CLIENT TIMEOUT — DO NOT RETRY THIS TOOL. Long-running LLM call (60-180s typical); MCP clients commonly close the call before the server returns. Retrying re-runs the 60-180s LLM call from scratch and burns compute. RECOVERY: the run_id is emitted in the FIRST notifications/progress event at t=0s (before the LLM call begins) — capture it. On timeout, call me.validation_history(run_id='<that-id>') to fetch the persisted result; the server-side run completes independently within a 20-minute budget. Edge case: if the transport dropped before the first progress notification (very rare; sub-second window), call me.validation_history(repository='<same value you passed here>') to find your most recent run. TASK-AUGMENTED INVOCATION (MCP 2025-11-25, SEP-1686): clients that advertise the tasks capability can task-augment this call by including task: {ttl: <ms>} inside the JSON-RPC request's params (NOT as a tool argument; alongside arguments, _meta, etc.). The server returns a CreateTaskResult immediately (taskId equals the run_id above) and runs the validation in the background. Spec-correct long-running pattern: poll via tasks/get for state, fetch the terminal payload via tasks/result, listen for notifications/tasks/status for push updates, and cancel via tasks/cancel. _meta.progressToken from the original request stays valid for the entire task lifetime. Sync (non-augmented) calls behave exactly as before, backwards-compatible by construction. The me.validation_history(run_id=...) recovery path remains the canonical recovery handle for clients that don't yet advertise the tasks capability. Returns code_classification (autonomous_agentic_workflow vs non_agentic_component), per-principle findings (verdict, severity_score 0-100, severity_class, code-cited evidence, recommendation), severity-weighted readiness (score|null, grade|null, tier ∈ {production_ready, emerging, draft, not_applicable}), recommended examples, reproducibility envelope (model, seed, doctrine_fingerprint, prompt_template_fingerprint), persistence_status with shareable run_id/badge_url/review_url. WHEN TO CALL: the user wants a governance audit, readiness score, or production_ready badge on an agent/workflow they just built or changed. WHEN NOT TO CALL: non-agentic plumbing (math utilities, type aliases, event-loop helpers, single-shot request/response handlers) returns tier=not_applicable with score=null/grade=null — that's not a failure, the doctrine simply doesn't grade non-agentic code, and architect.certify will refuse with not_agentic_component. Submit the OWNING agentic workflow instead. BEHAVIOR: long-running LLM call (~60-180s typical at high reasoning effort, single-pass; server-side budget 20 min). Mints run_id at t=0; first notifications/progress event carries run_id as recovery handle; keepalive every 30s. Persists ValidationRun + UserValidationRun + AIValidationRunLog + LLMUsageLog atomically; on rollback, badge/review URLs are stripped. Auth: Bearer , Pro/Teams plan. UK/EU residency; transient OpenAI processing (no-training); prompt-injection in code is inert. INPUTS: send FULL file contents verbatim as implementation_context (NO truncation, NO ... placeholders, NO comment removal — the architect treats your ... as literal code and hallucinates bugs that don't exist). If too large, split into MULTIPLE calls scoped by file/module; never truncate one call. Pass repository="" to group runs into a project trend. Pass private_session=true to skip the stored run (persistence + recovery disabled); operational security + cost logs are still kept. focus_area narrows scope; unmatched focus_area fails explicitly rather than silently widening. PAYLOAD COMPLETENESS (load-bearing if you intend to architect.certify this run): the validate first-pass is permissive — it scores on doctrine alignment + structural patterns visible in the submitted code. Cert's adversarial second-pass is rigorous — it scores on cert-payload-completeness as well as code correctness. A run that scores 100/A at validate can cert-reject pre-LLM with payload_incomplete when imported modules' surfaces aren't visible. To validate with INTENT TO CERT, also bundle verbatim public-surface stubs for every imported module: from sqlalchemy.exc import SQLAlchemyError → include a stub class; from app.db import models → include a class models: namespace stub with the columns/methods the code references; module-level imports of dataclass, Literal, json, datetime, timezone MUST also be in the payload (cert correctly catches when they're omitted — the module would NameError on import as submitted). 'Submit Like Production': the payload should be the code as it would actually run. TWO COMPLETENESS AXES. (1) IMPORTS: stub the public surface of every dependency (above). (2) ENFORCEMENT BRANCHES: the code under cert itself (approval gates, policy checks, recovery paths) must be the REAL logic, fully written. A placeholder body (# ... execute approved action ..., pass # TODO, a bare ...) is graded as a MISSING control, not shorthand; cert scores what would actually run. Never sketch the agent you are certifying. Empirically reconfirmed PR #157 iter8 → iter9 cert downgrades. SCORE VARIANCE DISCLOSURE (anomaly #10 — empirically documented): validate scores are POINT ESTIMATES with an observed empirical variance band of ~20-67 pts on BYTE-IDENTICAL input. Runs against the same repository, same code, same deterministic seed (the seed is derived from input — same input → same seed) can produce materially different scores AND different top-blocker rankings, because OpenAI's reasoning models at reasoning_effort=high are not strictly deterministic even with the seed parameter pinned. The reproducibility_mode='best_effort' field on every response is the platform's honest disclosure of this property. For decisions where stability matters more than speed, call architect.validate_consensus (N=3-5 aggregated, median verdict + per-principle stability metrics) instead — collapses the variance, surfaces unstable principles explicitly. A single validate run is a single roll; consensus is the right tool when one score isn't enough. ITERATION LOOP — repository keying. Pass the SAME repository value across calls to chain iteration rounds; the validator auto-resolves the most recent prior run on (user, repository, scope) as prior_run_baseline and the LLM grades the new submission with iteration context (per-principle severity deltas surface in the response). Changing the repository string between calls — even subtly with an iter-2 suffix — silently severs the chain and yields a fresh blind first-shot. Round numbering belongs in task or commit messages, never in repository. See the architect-validation-orchestration skill in the agent-asset pack for the full validate → consensus → certify sequence. VERIFICATION LAYERS (the two-layer doctrine this platform practices on itself): validate verifies DOCTRINE ALIGNMENT against the 10-principle Blueprint — design patterns, hand-off explicitness, operational-state inspectability, race/blocker handling at the architectural level. validate does NOT guarantee runtime correctness. cert verifies PAYLOAD COMPLETENESS and runs an adversarial second pass over the submitted code — catches production_blockers the first pass missed, name-errors on import, missing module surfaces, etc. cert does NOT verify runtime correctness either. Passing validate is a NECESSARY condition for production_ready, not a sufficient one. Runtime correctness (does this actually execute and behave?) is verified at the THIRD layer — your tests, types, walks. The platform's own recursive-integrity practice: every PR runs validate against its own primitives, then cert. Real bugs surfaced via this practice in PR #157 — NULL-UUID false-positive (iter3) and tie-breaker mismatch (iter5) — that 25 unit tests had missed. Two-layer verification is the discipline, not 'either/or'. TYPED FAILURES: timed_out, rate_limited, dependency_unavailable, schema_mismatch (each carries retryable + next_action). NEXT STEP: if tier=production_ready (A or B grade), the response carries certification_status='not_evaluated' — call architect.certify(run_id, code) to mint the certified production_ready badge (separate ~60-150s adversarial review, eligibility-gated). See Payload Completeness above for the common pre-cert pitfall.

Pro/Teams — first-pass surface-craft review of a FRONTEND artefact (component, screen, or flow) against the 8 laws of the Experience Design Blueprint. The surface-craft companion to architect.validate: where architect.validate scores agentic ARCHITECTURE against the 10 agentic principles, design.validate scores the PERCEPTIBLE SURFACE — what the user sees, taps, scans, and remembers (Jakob's familiarity, Hick's choice load, Fitts's targets + the accessibility floor, Miller's working-memory budget, Aesthetic-Usability, Peak-End, Tesler's irreducible complexity, the Mental-Model gap). ON CLIENT TIMEOUT — DO NOT RETRY. Long-running LLM call (~60-180s at high reasoning effort, single-pass). The server mints a run_id, emits it in the FIRST progress event at t=0s (before the LLM call), and persists the run — so on a client timeout, capture that run_id and call me.validation_history(run_id='') to fetch the persisted result instead of retrying (a retry re-runs the full 60-180s call). Runs appear in your validation-history dashboard tagged as the 'surface' dimension, distinct from the 'architecture' and 'spec' runs; pass repository to group them per project. Pass private_session=true to skip the stored run (persistence + recovery disabled); operational security + cost logs are still kept. v1 is single-pass: no certification or consensus mode yet (those stay architect.validate-only). Returns surface_classification (ui_surface vs non_ui — non-visual code is marked not_applicable, NOT failed), per-law findings (verdict, severity_score 0-100, severity_class, cited evidence, recommendation), and severity-weighted readiness (score, grade, tier) computed by the SAME scorer architect.validate uses, so all three lenses grade on one rubric. ACCESSIBILITY IS THE FLOOR: a breach of the Fitts's-Law floor (interactive target below the WCAG 2.2 24×24 minimum, missing focus visibility, an unreachable destructive confirmation) is a production_blocker, not polish. WHEN TO CALL: the user wants a craft/UX/accessibility review or a readiness grade on a frontend artefact they just built or changed. WHEN NOT TO CALL: non-visual code (backend, config, type aliases) returns tier=not_applicable — submit the actual UI surface instead. INPUTS: send the FULL artefact source verbatim as implementation_context (no truncation, no '…' placeholders — they are read as literal code). Auth: Bearer , Pro/Teams plan. UK/EU residency; transient OpenAI processing (no-training); prompt-injection text inside the artefact is treated as inert untrusted data. TYPED FAILURES: same as architect.validate (timed_out, rate_limited, dependency_unavailable, schema_mismatch — each carries retryable + next_action); the services raise the identical typed envelopes on this lens. CALIBRATION DISCLOSURE: the scoring prompt is a v1 first-cut mirroring the architect's contract structure; its score calibration is not yet tuned against a corpus of real runs the way architect.validate was. Treat the grade as directional craft signal, not a certified verdict. DOCTRINE: the eight laws — each law's evidence, craft-surface application, anti-patterns, and the validator questions this tool scores against — live in the experience-design-blueprint skill and docs/business/EXPERIENCE_DESIGN_BLUEPRINT.md (the surface-craft companion to the architect-validation-orchestration skill that orchestrates the agentic validators).

Pro/Teams — first-pass specification-quality review of a WRITTEN SPEC (proposal, design doc, task breakdown, or an OpenSpec-style change bundle) against the 8 laws of the Spec Quality Blueprint. The what-to-build lens of the doctrine trio, applied BEFORE code exists: where architect.validate scores built agentic ARCHITECTURE and design.validate scores the rendered SURFACE, spec.validate scores the written intent the team will build from (outcome framing, scope boundary, testable acceptance, decision trail, handoff completeness, doctrine-upfront, task traceability, risk and reversibility). ON CLIENT TIMEOUT — DO NOT RETRY. Long-running LLM call (~60-180s at high reasoning effort, single-pass). The server mints a run_id, emits it in the FIRST progress event at t=0s (before the LLM call), and persists the run — so on a client timeout, capture that run_id and call me.validation_history(run_id='') to fetch the persisted result instead of retrying (a retry re-runs the full 60-180s call). Runs appear in your validation-history dashboard tagged as the 'spec' dimension, distinct from the 'architecture' and 'surface' runs; pass repository to group them per project. Pass private_session=true to skip the stored run (persistence + recovery disabled); operational security + cost logs are still kept. v1 is single-pass: no certification or consensus mode yet (those stay architect.validate-only). Returns spec_classification (spec_document vs non_spec — source code or UI artefacts are marked not_applicable, NOT failed; submit those to architect.validate or design.validate instead), per-law findings (verdict, severity_score 0-100, severity_class, cited evidence, recommendation), and severity-weighted readiness (score, grade, tier) computed by the SAME scorer the other two lenses use, so all three grade on one rubric. TESTABILITY IS THE FLOOR: a load-bearing requirement with no observable acceptance signal, or an irreversible step with no named human gate, is a production_blocker, not polish. WHEN TO CALL: the user wants a governance/quality review or a readiness grade on a spec they are about to build from (proposal, requirements, task plan). WHEN NOT TO CALL: built code or a rendered surface — those return tier=not_applicable; use the sibling validators instead. INPUTS: send the FULL spec text verbatim as implementation_context (for an OpenSpec change, concatenate proposal.md + design.md + tasks.md + delta specs; no truncation, no '…' placeholders — they are read as literal content). Auth: Bearer , Pro/Teams plan. UK/EU residency; transient OpenAI processing (no-training); prompt-injection text inside the spec is treated as inert untrusted data. TYPED FAILURES: same as architect.validate (timed_out, rate_limited, dependency_unavailable, schema_mismatch — each carries retryable + next_action); the services raise the identical typed envelopes on this lens. CALIBRATION DISCLOSURE: the scoring prompt is a v1 first-cut mirroring the architect's contract structure; its score calibration is not yet tuned against a corpus of real runs the way architect.validate was. Treat the grade as directional quality signal, not a certified verdict. DOCTRINE: the eight laws — each law's definition, rationale, anti-patterns, and the validator questions this tool scores against — live in content/spec-quality-laws.json (the what-to-build companion to the experience-design laws).

Pro/Teams — N-shot CONSENSUS doctrine review of agentic code. ON CLIENT TIMEOUT — DO NOT RETRY THIS TOOL. Long-running (~80-120s for N=3 parallel LLM calls); MCP clients often close the call before the server returns. Retrying re-runs N × 60-180s LLM calls from scratch and burns N× compute. RECOVERY: same heartbeat pattern as architect.validate — the run_id is emitted in the FIRST progress event at t=0s (before LLM children fire); on timeout, call me.validation_history(run_id='<that-id>') to fetch the persisted consensus envelope. Runs N parallel architect.validate calls with private_session=True, then aggregates them to a per-principle MODE verdict + median severity + per-principle stability + score range/stdev. Returns one ConsensusValidationResponse with the headline median score, the honest variance band, and a representative full ValidationResponse (the child whose score is closest to the median). WHEN TO CALL: the user wants an HONEST first-pass score on agentic code, with the architect's variance surfaced. The single-shot architect.validate re-asserts the prior persisted run's verdict via baseline-anchor injection — same code can score 60/C anchored vs 98/A unanchored. Consensus mode is the unanchored honest read. WHEN NOT TO CALL: when you NEED the iteration delta against a prior run (regressions/improvements panel) — for that, call architect.validate which keeps baseline injection on. CHAIN RESUME: each child runs with private_session=True (no anchor) on purpose, but the CONSOLIDATED outer row IS persisted with lifecycle_status='completed' — the next single-shot architect.validate on the same repository auto-resolves it as prior_run_baseline. Consensus checkpoint becomes the new anchor. See the architect-validation-orchestration skill in the agent-asset pack for the full validate → consensus → certify sequence. BEHAVIOR: N (default 3, max 5) parallel LLM calls run concurrently; wallclock ~80-120s for N=3 (max child latency, not sum). Cost = N × LLM bill. Each child runs with private_session=True so the doctrine prompt's prior-run baseline injection is suppressed (no anchor bias). One CONSOLIDATED UserValidationRun row is written carrying the consensus envelope; the N children themselves do NOT persist (private_session contract). AUTH: Bearer , Pro/Teams plan. Same paid-plan gate as architect.validate. INPUTS: same shape as architect.validate. n is the only extra arg (range 2..5). private_session is implicit (always true for children); the OUTER consolidated row IS persisted unless the tool itself is called inside another private context — but no such wrapper exists today. OUTPUT: response carries score_consensus_median (headline), score_stdev (honest uncertainty), score_range (min, max), mode_stability_min_pct (the cert-eligibility gate's input — ≥ 80% means the consensus is stable), per_principle (mode + distribution + severity median per principle), and representative_response (the closest-to-median child's full ValidationResponse so existing UI components render unchanged). TYPED FAILURES: same as architect.validate (timed_out, rate_limited, dependency_unavailable). Plus consensus-specific: consensus_quorum_failed when fewer than 2 child runs succeeded (≥ 2 required to compute a meaningful median).

Pro/Teams — second-pass adversarial certification of an architect.validate run that scored production_ready (A or B first-pass tier). ON CLIENT TIMEOUT — DO NOT RETRY THIS TOOL. RECOVERY FIRST: the run_id is emitted in the FIRST notifications/progress event at t=0s (BEFORE the LLM call begins). Capture it. On timeout, call me.validation_history(run_id='<that-id>') to fetch the persisted cert verdict; the server-side run completes independently within a 20-minute budget. This is the canonical recovery path. Use it before considering any retry. Long-running LLM call (60-180s typical; exceeds Claude Code's ~60s idle budget); MCP clients commonly close the call before the server returns. Retrying re-runs the LLM call AND burns one of your 3 cert retry-budget attempts. Mints the certified production_ready badge when both reviewers sign off; caps the run to C/emerging when the second pass surfaces a missed production_blocker. MANDATORY DOCTRINE RULE (load-bearing): the badge certifies the EXACT code that produced the validate run_id, NOT 'this codebase' in general. If you modify, fix, or iterate the code between architect.validate and architect.certify — even a single character — cert rejects with code_fingerprint_mismatch. Fixing the code voids the run. The recovery path is always: edit code → architect.validate → fresh run_id → architect.certify on the fresh run. Do NOT cert from a stale run_id after iteration; ask the user to re-validate first. WHEN TO CALL: only after architect.validate returned tier=production_ready AND the user wants the certified badge AND the code has not been touched since the validate run. NOT for tier=draft/emerging/not_applicable runs (typed rejections fire — see below). NOT idempotent across attempts: each call is one of the 3 attempts in the retry budget. BEHAVIOR: atomic one-shot single LLM call, ~60-180s server-side at high reasoning effort (small payloads finish faster; observed p99 ~250s; server-side budget is 20 min, ~5× observed max). Exceeds typical MCP-client tool-call idle budget (~60s in Claude Code), so the FIRST notifications/progress event fires at t=0 carrying the run_id. The run is atomic by contract — no in_progress lifecycle, no cancellation, no resume. Updates the persisted run's result_json (public review URL + me.validation_history(run_id=...) reflect the cert outcome). ELIGIBILITY GATE (typed rejection enum on failure): caller must own the run, tier=production_ready, less than 24h old, not already certified, within cert retry budget (max 3 attempts), no other cert call in flight for the same run_id, code fingerprint must match the validated code, AND the submitted payload must be cert-payload-complete (see Payload Completeness below — cert rejects pre-LLM with payload_incomplete when an imported module's surface isn't visible in the validate payload that produced this run_id). Rejection reasons (typed Literal): auth_required, paid_plan_required, run_not_found, not_run_owner, not_eligible_tier, not_agentic_component (tier=not_applicable runs), already_certified, certification_age_exceeded, retry_budget_exhausted, code_fingerprint_mismatch, code_fingerprint_missing, code_not_on_file (caller omitted code argument AND the 24h cert-retry hold for this run has expired or was never written. Recovery: re-run architect.certify from the same MCP session that ran architect.validate, passing the code explicitly — the server never persists code by design), payload_incomplete (submitted/validated payload imports modules whose contents aren't visible — cert refuses pre-LLM to prevent a false-precision downgrade. Recovery: re-validate with verbatim public-surface stubs for every imported module, then re-cert on the fresh run_id. Empirically validated: PR #157 iter8/iter9 cert rejections were exactly this class — code on disk was correct, the submitted payload merely omitted module visibility), cert_consensus_score_below_threshold (consensus_median<75 — consensus runs only), cert_consensus_unstable_blocker (any principle mode_stability<80% — consensus runs only), run_state_corrupt, cert_persistence_failed, cert_in_flight (a prior architect.certify call on this run_id is still running. Poll me.validation_history for the verdict; do not retry until it resolves). PAYLOAD COMPLETENESS (load-bearing for cert eligibility): the cert reviewer reads the EXACT payload that produced the validate run_id. Imported modules whose surface isn't present in the payload cause pre-LLM payload_incomplete refusal. Avoidance — when validating with intent to cert, bundle public-surface stubs for every imported module: from sqlalchemy.exc import SQLAlchemyError → include a stub class; from app.db import models → include a class models: namespace stub with the columns/methods you reference; module-level imports of dataclass, Literal, json, datetime, timezone MUST also be in the payload (cert correctly catches when they're omitted — code would NameError on import). 'Submit Like Production': the payload should be the code as it would actually run, not a compressed sketch. The stubs cover IMPORTED dependencies only; the certified code's own enforcement branches (approval gates, policy checks, recovery paths) must be present in full. A # ... placeholder reads as an ABSENT control and is graded against you, not as shorthand for one that exists. PRE-LLM REJECTION AUDIT TRAIL: when cert rejects before the LLM call (payload_incomplete, code_fingerprint_mismatch, etc.), certification_attempts=[] on the response — no attempt landed in the retry budget, no LLM hop occurred. The rejection envelope's rejection_reason + guidance are the actionable surface. (Audit-trail UI surfacing of pre-LLM rejections is tracked in the platform self-audit set as anomaly #5; out of scope for the cert tool itself.) INPUTS: re-send the SAME code that produced the run_id (the architect persists findings + recommendations, never code, by design — privacy-preserving). Server compares the submitted code's SHA-256 fingerprint to the stored fingerprint and rejects mismatches. Auth: Bearer , Pro or Teams plan required. UK/EU data residency (Cloud Run europe-west2). Code processed transiently by OpenAI (no-training-on-API-data) and dropped; payloads JSON-escaped + delimited as inert untrusted data — prompt-injection inside code is ignored. If the cert call fails outright (provider error, persistence error), a fresh architect.certify is the recovery path; the eligibility gate enforces the 3-attempt retry budget. For long-running cert workflows the answer is to re-validate, not to make this tool stateful. OUTCOMES: certification_status ∈ {confirmed_production_ready (badge mints), downgraded_to_emerging (cert review surfaced a missed production_blocker, tier capped at C/emerging), unavailable_provider_error (LLM call failed, retry within budget)}. Cert findings + summary + attempt history surfaced on the persisted run for full inspectability.

Pro/Teams — summarises the caller's tool-usage patterns and value signals over a configurable window (default 30 days). Returns tool_call_counts, top principles cited in validate runs, value_event_counts by event_type, and an aggregate readiness trend. WHEN TO CALL: the user asks 'how is the Blueprint helping me/my team', 'what should I explore next', or 'show me my Blueprint usage'. WHEN NOT TO CALL: proactively or on every conversation turn (the summary is an explicit retrospective, not telemetry); to compare users (returns only the caller's own data). BEHAVIOR: read-only, idempotent over the same window. Aggregates from AIToolCallLog + ValueEvent + AIValidationRunLog. Pass private_session=true to bypass server-side logging for this summary call (the underlying historical data still exists; only this read is untracked). Auth: Bearer , Pro or Teams plan. UK/EU residency.

Authenticated — returns the caller's Blueprint learning-path state: current course slug, stage progress, certification status (Foundation, Practitioner, Capstone), Capstone track eligibility flags, and the next recommended stage. WHEN TO CALL: the user asks 'where am I', 'what's next', or 'am I Capstone-eligible'; before suggesting next-step coaching content. WHEN NOT TO CALL: as a heartbeat (state changes only when the user completes a stage); to read another user's progress. BEHAVIOR: read-only, idempotent. Auth: Bearer (any plan, including basic). Returns user_email, course_slug, stages list with completion timestamps, certification block, and a next_stage hint.

Authenticated — returns stages in the caller's active course where recorded evidence is thin relative to the stage's principle requirements. Each thin stage carries the missing principle slugs + a short diagnostic so the caller can suggest the user record concrete evidence. WHEN TO CALL: when the user asks 'what should I work on next' or 'what's weak in my Blueprint progress'; before suggesting which guide/example to consult. Pair with me.add_evidence to close gaps. WHEN NOT TO CALL: to lecture the user on principles they have already satisfied; on every conversation turn (state changes only when evidence is added). BEHAVIOR: read-only, idempotent. Auth: Bearer (any plan). Returns thin_stages list with stage slug, course slug, missing principles, evidence_count, and a coaching_note.

Authenticated — append a free-text evidence note to a specific stage in the caller's active course. Notes record concrete implementation observations, decisions, or artefacts that demonstrate progress through a Blueprint principle (e.g. how a delegation boundary was implemented, what approval flow was chosen and why). Persisted as UserStageEvidence rows scoped to (user_id, course_slug, stage_slug). WHEN TO CALL: AFTER the user has articulated something concrete they have built, observed, or decided — not to capture intent or speculation. Pair with me.coaching_context to close evidence gaps. WHEN NOT TO CALL: to log every conversation turn; to record planning, ideas, or todos; on behalf of another user; without the user's awareness (they should know their progress is being recorded). BEHAVIOR: write-only, single insert. Auth: Bearer (Firebase ID token, any plan). UK/EU residency. Notes are visible only to the owning user and are surfaced on me.learning_path / me.coaching_context. Confirms the stage_slug + course_slug pair in the response so the user can see which stage was credited.

Pro/Teams — list or inspect the authenticated user's Governed Sessions (GEP-M2): durable, owner-scoped containers that group validation runs across lenses (architect.validate → 'architecture', design.validate → 'surface', spec.validate → 'spec') into one timeline for one piece of work. Two modes: (1) No arguments returns every session (id, title, status, repo_url, spec_ref, team_agents, run_count, validators = the lenses seen), newest first. (2) session_id=<id> returns that session plus its run timeline (light rows; fetch full results per run via me.validation_history(run_id=...)) and, for team sessions, events = the typed team-event log posted via me.session_event. Attach new runs by passing session_id to architect.validate, design.validate, or spec.validate. Sessions are created and managed in the web app at /app/sessions. Read-only. Auth: Bearer . Pro or Teams plan required.

Pro/Teams — append a TYPED TEAM EVENT to a Governed Session's timeline (GEP-M6). This is how the user's own harness makes trio work inspectable: handoffs between role lenses, pushbacks, plan previews, gates, and acks land as structured events next to the validation runs, so the session reads as a system, not a transcript. CHANNEL PROVENANCE: this MCP channel posts the AGENT-SIDE vocabulary only. steer events and actor human are cockpit-originated by contract (the owner posts them from the AIDB Studio session surface) and are REFUSED here, so a timeline entry can never impersonate the human side of the loop. Every event posted here is durably stamped with its channel. REQUIRES team mode: the session must have team_agents enabled (toggled in the web app on the session page); posting to a standalone session is refused so non-team sessions stay byte-identical. Owner-scoped: foreign session ids read as not found. event_type: handoff | pushback | plan_preview | gate | ack. actor: pm | engineer | designer | system. Read events back via me.sessions(session_id=...). WHEN TO CALL: at every role handoff (who -> who, what was passed), when a role pushes back on another's output, when the PM's plan is previewed for the co-planning gate, and when a hard gate blocks on an irreversible side-effect. ack: the IDE agent confirms it STARTED working on a steer. Post it FIRST on receiving a steer (summary like 'Started: '), then execute, then post handoff with the result. WHEN NOT TO CALL: not a chat log: post decisions and transitions, not every message; never to record a steer (steers arrive FROM the cockpit via me.await_steer). REJECTION CODES (invalid_request): 'Session not found.' (not yours, or no such id); 'Team mode is off for this session.' (owner enables it on the session page); 'This session has reached its event limit (500).' (the shared volume brake: start a new session for further team events); 'summary must not be blank.' (empty summaries are refused); steer/human posts are refused with a pointer to the cockpit channel. Auth: Bearer , Pro/Teams plan.

Pro/Teams. BLOCK until the session owner posts the next steer event to a Governed Session from the AIDB Studio cockpit, then return it. DELIVERY GUARANTEE: the durable cursor read against the session log is authoritative (at-least-once: a lost response is safely re-issuable with the same cursor, and timed_out is only returned after a final confirming read). The in-between wake-up is a best-effort in-process push: usually sub-second, but a steer is never lost if a wake-up is missed; the confirming read catches it. See the after_event_id and timeout_s parameter descriptions for the semantics. THE LOOP: finish a task -> post me.session_event handoff -> call me.await_steer -> on a steer, FIRST post me.session_event event_type=ack ('Started: '), then execute, then handoff, then call me.await_steer again; on timed_out, call again with the returned after_event_id. REQUIRES team mode on the session (toggled by the owner in the web app); owner-scoped, so foreign session ids read as not found. Read-only: this tool never writes events. REJECTION CODES (invalid_request): 'Session not found.' (not yours, or no such id); 'Team mode is off for this session.' (owner enables it on the session page). Auth: Bearer , Pro/Teams plan.

Pro/Teams — return the authenticated user's validation run history for all three lenses (architect.validate → validator='architecture', design.validate → validator='surface', spec.validate → validator='spec') with the Blueprint Readiness Score (0-100), letter grade (A-F), and tier (draft, emerging, production_ready). Each run carries a validator field naming its lens. Three lookup modes: (1) run_id=<id> returns a SINGLE run with the full persisted result_json — use this to RECOVER a result when your MCP client tool-call timed out before architect.validate, design.validate, or spec.validate returned. The run completes server-side and persists; the run_id is surfaced in the first progress notification of every validate call so you have the recovery handle even when your client gives up early. (2) repository=<name> returns the full per-run trend for that repository plus a regression diff between the latest two runs. (3) No arguments returns one summary per repository the user has validated, sorted by most recent. Use modes (2) or (3) BEFORE re-validating the same repository on either lens — they tell you which principles or laws regressed since the last run, so you can focus the new review on what is actually changing. Auth: Bearer . Pro or Teams plan required.

Authenticated — creates a support handoff record when an agent needs human review, account-specific escalation, or operator follow-up that cannot be resolved with the read-only doctrine tools. Persists a SupportHandoff row (reason, topic, page_url, agent_name, agent_platform, trace_summary, user_email) routed to the support inbox; user is contacted by the team. WHEN TO CALL: user explicitly asks for human help, hits a billing/access issue, or the agent has tried the doctrine tools and the user still needs a human. ALWAYS confirm with the user before firing — this creates a human-visible ticket. WHEN NOT TO CALL: proactively, silently, or to log debugging traces (use diagnostic logs instead); for partnerships/agency enquiries (use handoffs.partnership / handoffs.agency); for content questions answerable by principles.search / guides.search. BEHAVIOR: write-only, single insert, side-effecting (creates a ticket the team will see). Auth: Bearer (any plan). UK/EU residency. Response confirms ticket id + topic so the user can reference it.

Authenticated — creates a partnerships handoff record for design-partner, ecosystem, training, or advisory conversations needing human review. Persists a PartnershipHandoff row routed to the partnerships inbox; the user is contacted by the team. WHEN TO CALL: user explicitly wants to engage as a design partner, co-marketing/training partner, or evaluate the Blueprint for their org's training programme. ALWAYS confirm with the user before firing — this creates a human-visible partnerships ticket. WHEN NOT TO CALL: for general support / billing / access issues (use handoffs.operator); for paid-engagement enquiries (use handoffs.agency); proactively or as a sales prompt — only when the user has explicitly asked. BEHAVIOR: write-only, single insert, side-effecting (creates a ticket). Auth: Bearer (any plan). UK/EU residency. Response confirms the ticket id + audience so the user can reference it.

Authenticated — submit an agency engagement enquiry on behalf of the caller for a founder-led discovery call. Persists an AgencyHandoff row routed to the agency inbox; the user is contacted by the team for a scoped proposal. Engagement scopes: workflow sprint (rapid agentic workflow implementation), proof-of-concept (validate a specific agent design in a bounded timeframe), pilot support (co-design and validate a production-ready pilot), advisory (ongoing architectural guidance across a product team). WHEN TO CALL: the user has identified a paid hands-on expert engagement need beyond self-service learning, and explicitly asks to talk to the team or book a discovery call. ALWAYS confirm with the user before firing — this creates a sales-visible record. WHEN NOT TO CALL: for free training / partnerships discussion (use handoffs.partnership); for support / billing / access (use handoffs.operator); proactively or as a sales push. BEHAVIOR: write-only, single insert, side-effecting. Auth: Bearer (Firebase ID token, any plan). UK/EU residency. Response confirms the ticket id + scope so the user can reference it.