Read from Unl
get_from_unlREAD from your Unlimitless substrate (read-only, workspace-scoped). Open what you were handed — every id the wake / ask_unl serves is openable here. The substrate is the system of record for settled decisions; conversational recall is not authoritative. action: 'open' — resolve ANY served id (8-char prefix or full uuid) to {type, statement/content, why, status, lane/scope} across EVERY object type (ruling, pillar, reflection, deliberation, brief, debt, momentum, target). 'walk' — from an id, traverse its genuine links (ruling/brief/deliberation edges + a pillar's references + ids noted in its prose) — walk the chain of whys to ground in full. 'hunt' — search across types (q text, type, recent) with COMBINABLE filters: status (canonical|superseded for rulings; work_in_progress|locked|completed|retired|superseded|parked for briefs; open|answered for stops; open|done for targets), authority_scope, constraint_type, lane, created_after/created_before (ISO), and governed_by (a ruling id → the briefs it governs). Each filter narrows to the types that carry it; results stay flat (relevance/recency, never priority-ranked). 'trace' — DECISION TRACE for a ruling id: the ruling + why, its deliberation CARCASS (pillars: options/tensions/rejected-alternatives/quotes), the supersession chain both ways (walked by machine keys), the refines lineage, and the derivation SHAPE read from the stored compaction (or 'shape not recorded' — never computed). Read-only, on-demand. 'export' — BULK EXPORT of THIS workspace as portable JSON (backup/portability/leaving). No export_section → the MANIFEST (per-table counts, edge count, declared exclusions). With export_section=<table|'edges'> [export_offset=N] → that section's rows, capped + paginated (has_more/next_offset). Faithful (rows as stored, incl. superseded/retired), workspace-scoped, read-only; the connector returns it — you place your backup. 'analytics' — READ from a tool the person has connected (their analytics, error tracking, search data, or another MCP server), server-side: the credential never leaves Unl. Keys: provider (default 'posthog') · op · body · target (+ q for queries, id for object ids). provider 'mcp' → the workspace's connected MCP servers (target = which connection by name/host; op 'tools' lists them, op= calls a tool that declares itself read-only; body = its arguments). provider 'feed' → connected public feeds (GET only; target = which feed). provider 'unl' → the person's own read-specs/bars: op 'specs' lists them · 'spec' (target=read_key) reads one · 'refresh' (target=read_key) re-reads now. Key providers (posthog | sentry | search_console | railway) take op 'http' with body={method, path, query, body} — the provider's own API request, signed with the stored credential and sent only to the host verified when it was connected. A GET, a GraphQL query, and a POST the provider documents as a read (Search Console's searchAnalytics query and URL inspection) are reads. posthog also has named reads: 'events'/'event_names' · 'query' (HogQL, SELECT-only, via q) · 'insights'/'insight'. This action only reads: a request that would change data in the tool is refused and nothing is sent — changes go through write_to_tool. Never reads the substrate. (analytics_* names are legacy aliases of op/body/target/name.) 'brief' — read ONE brief: full content + ordered steps, owner, state, lane/rank, governed_by, target served (by brief_id OR lane+order_rank). Generated currency history and large typed cargo fold to report ids and source pointers; original text is never rewritten. For exact original pages use action=brief, path=content|cargo|waiting_on and export_offset=0, then follow next_offset until has_more=false; each page carries the source SHA256. 'list' — list briefs by lane and order. 'open_pack' — FETCH A PACK TO RUN IT: renders the ordered brief REFERENCES (each resolved to its brief AT FETCH TIME, so a brief closed since the pack was composed is caught by skip-if-closed), the per-item fences, and the standing run directives. BY REFERENCE — read each brief at source (action=brief) as you reach it; the pack never carries content. First fetch advances the pack composed→dispatched; its run report (log_to_unl kind=run_report, pack_id) closes it. 'agent_frame' — WHAT'S IN AGENT FRAME: the held set of proposals an agent filed via POST /api/v1/propose, each an addressable held item with its why, its agent-REPORTED state (unl exposes the field, never defines the state machine), and the position(s) it bears on. Distinct from your own reflections in the soil; open any by its 8-char id for the full item + edges. Read-only. 'path' — the FULL Critical Path in one call: every OPEN brief in master_order (all N, not just the wake's top-10), each with lane, per-lane rank, master position, state, waiting_on, autonomy, governed_by + depends_on edges, target, and order-why. 'templates' — list the ways of working (momentum-log templates) available to this workspace: key, name, one-line, who-for, surface, and which is ACTIVE (▶). Switch/author them via manage_unl. 'projections' — list the configured projection targets (project the substrate OUT to CLAUDE.md/AGENTS.md/doc/Notion): type, scope, destination, last-refreshed. Configure/refresh/remove via manage_unl. 'risks' — the RISK REGISTER (read-only panel): every live risk with severity (Claude-applied indicator, NOT a priority order) · status (open|worked|closed) · resolution · links. — GIT (READ-ONLY, the neilmortimer-kar/unlimitless repo — reference, cite as repo-sourced NEVER canon; verify CC's code claims against the actual repo): 'repo' — repo metadata + recent commits + a directory listing (optional ref, optional path). 'file' — a file's contents at a ref (path required; ref optional → default branch). 'search' — code/path search WITHIN the repo (q required; repo-scoped, can't range outside). Ambiguous id-prefixes REJECT and ask for more characters — never the wrong object.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | [constraints] field or limit name; q=write_scorecard reads measured first-try writes by declared receiver · [hunt] text across object types · [search] code/path text within the repo. | |
| id | No | [open/walk] the id to open/walk — the 8-char prefix the wake/ask_unl shows, or a full uuid; resolved across all object types, ambiguity rejects. [open_pack] also accepted as the pack id. | |
| op | No | [analytics] the provider op (e.g. http | events | event_names | query | insights | insight | specs | spec | refresh | tools). | |
| ref | No | [file/repo] optional git ref — branch, tag, or commit sha (defaults to the repo's default branch). | |
| body | No | [analytics] the request: for op 'http', { method, path, query?, body? }; for an MCP tool, its arguments. | |
| full | No | open / walk / file / analytics: reads come SHORT FIRST — every field present, long ones cut to a first page with the size of the rest named, edges past the first few counted — and whole on full=true. Nothing is filtered either way. | |
| kind | No | [hunt] momentum only — the beat kind, e.g. run_report | stop | handoff | rejection. THE HANDOVER LANE: a run report sinks below a recency hunt within minutes on a busy board (64% of momentum is automatic bookkeeping), so ask for the kind you want rather than for recent beats and hope. Narrows to momentum; other types are excluded honestly. | |
| lane | No | [brief] paired with order_rank · [list] optional lane filter. | |
| path | No | [brief] original source field: content, cargo or waiting_on (paged with export_offset and limit, maximum 16000 characters); [file] required file path (e.g. 'src/mcp/server.ts') · [repo] optional subdirectory to list. | |
| type | No | [hunt] optional type filter: ruling | pillar | reflection | deliberation | brief | debt | momentum | target. | |
| limit | No | [brief with path] original-source page characters (at most 16000) · [list/hunt] max rows · [search] max git matches. | |
| action | Yes | constraints (generated field limits and refusal templates before writing: q=<field or limit name>, export_offset for the next page, full=true for all matching entries) · substrate: open|walk|hunt|brief|list|open_pack|agent_frame|path|templates|projections|trace|export|risks · usage (the person's Unl plan and this week's usage, in plain words) · clean_serves (the clean-serve count and the latest verdicts, to tell the person in plain words) · serve_log (what Unl told your AI: when the person asks "what did Unl tell you?" or which decisions reached which agent — this conversation's serves by default, id="all" for every serve, id=<surface or agent> for one) · receivers (how Unl reads the person's use of each AI, from their own messages: a working hypothesis, never their decision; when they ask what Unl thinks they use an AI for) · fleet (every fleet agent's own last report: working, waiting on CI or the person, idle, at the usage limit; pass id=<agent> for one agent's history) · readiness (the alpha launch readiness view: each line ready only with its proof, the order once started, what pauses it) · analytics (PostHog, server-side) · git (read-only): repo|file|search. | |
| recent | No | [hunt] order by recency (most recent first). | |
| status | No | [hunt] status filter: canonical|superseded (rulings/pillars) · work_in_progress|draft|locked|completed|retired|superseded|parked (briefs) · open|answered (stops: open = answered_at unset, the rows every waiting-count counts) · open|done (targets). Narrows to the types that carry it. | |
| target | No | [analytics] which object or connection (e.g. an MCP connection's name, a read-spec's read_key). | |
| pack_id | No | [open_pack] the pack id or unique id-prefix to fetch and run (the id filed by manage_unl file_pack / dispatched as 'run pack <id>'). | |
| brief_id | No | [brief] full uuid OR unique id-prefix; reaches unranked briefs too. (Also accepted as the id for open/walk.) | |
| provider | No | [analytics] the provider to reach — default 'posthog'. | |
| order_rank | No | [brief] rank within the lane — 'do <lane> brief N'. | |
| governed_by | No | [hunt] a ruling id/prefix — return the briefs governed_by it (combinable with lane/status/date). | |
| analytics_op | No | [analytics] legacy alias of op. | |
| created_after | No | [hunt] ISO date/time — only items created on/after this. | |
| export_offset | No | [brief] original-source character offset when path=content|cargo|waiting_on; [export/constraints] row offset for the section (paginate via the response's next_offset until has_more=false). | |
| session_token | No | EVERY substrate read (open/walk/hunt/brief/list/path/trace/agent_frame/open_pack/risks/templates/projections/export): THIS chat's [unl-session:] token, echoed verbatim, so the read serves the project this conversation is in rather than every project in the account (one gate, all lanes). Omit it and the read falls back to your sole venture; with several ventures and a turn that could not be placed it REFUSES and names them. It never guesses which venture you meant. The git reads (repo/file/search) ACCEPT it too and do not need it: without it they read the venture this connection declared at connect_to_unl, and every answer names which venture it read and how. | |
| analytics_body | No | [analytics] legacy alias of body. | |
| analytics_name | No | [analytics] convenience name for create ops (folded into body); legacy. | |
| created_before | No | [hunt] ISO date/time — only items created on/before this. | |
| export_section | No | [export] the section to fetch — a table name from the manifest, or 'edges'. Omit for the manifest. | |
| authority_scope | No | [hunt] rulings only — match rulings whose authority_scope overlaps any of these tags. | |
| constraint_type | No | [hunt] rulings only — budget|sequencing|architectural|commercial|language|governance|schema|positioning. | |
| analytics_target_id | No | [analytics] legacy alias of target. |