Query the knowledge graph for facts about entities (APIs, functions, classes, etc.)

Record a development event (file edit, test run, etc.)

Validate a proposed code change against known constraints

Get constraints (linting rules, patterns, conventions) for a file

Record a user correction to Claude's output (high-priority learning signal)

Get bugs fixed in a file and assess regression risk

Scan the project codebase and populate the knowledge graph with entities and relationships from existing code

Pull GitHub PR review comments and convert them into learned constraints in the knowledge graph

Record a decision trace: what the agent proposed and how the human responded

Attach a signed human annotation (note, override rationale, or intervention record) to a span of agent events. Persists into the annotations table and chains into the same Merkle audit log as agent writes (v0.15.0, ADR-0001). Rationale limited to 8 KB.

Get decision traces showing agent proposals and human corrections

Record test results and link failures to recent code changes

Get files commonly edited alongside the given file based on historical patterns

Search entities across all registered world-model projects

Score regression risk for a proposed change to a file based on past bugs, test failures, and constraint violations

Project blast radius and historical outcomes for a proposed change

Surface tests likely to fail given a set of edited files

Promote a constraint from this project to all other registered projects

Memory health diagnostics: orphans, stale facts, contradictions, decay candidates, DB sizes

Pre-action context bundle: constraints, decisions, bugs, co-edits, related facts, and risk score for a file before editing

Find pairs of facts that contradict each other based on similarity and status differences

Hydrate a Claude Code session transcript by line range. Lets agents trace a fact back to the exact conversation that produced it.

Generate a CLAUDE.md document from the knowledge graph (top constraints, recent decisions, known bug regions, co-edit patterns).

Return a compact constraint+fact bundle for PostCompact / UserPromptSubmit hooks to re-inject after context loss.

Record a context-compaction event with token counts and what was re-injected. Lets developers audit what was remembered across compaction boundaries.

List recent compaction audit entries, most-recent first. Filter by session_id or limit count.

Parse AGENTS.md / CLAUDE.md / GEMINI.md / .agents/skills/*.md in the project and return declarative constraints. Mixed into PreToolUse enforcement automatically; this tool exposes the same data for inspection.

Pick a winner between two contradicting facts using a confidence-weighted strategy (auto, keep_higher_confidence, keep_most_recent, keep_most_sources, supersede_a, supersede_b, manual).

Adversarially verify an answer is grounded in a specific set of facts. An independent Coach LLM call checks each material claim in the answer against the supplied source facts and returns confidence (HIGH / MEDIUM / LOW), verified + unverified claim lists, and per-claim source_pointers. Never raises; failures return LOW + error populated. v0.12.12.

v0.13 tamper-evident audit log. Return a cryptographic inclusion-proof bundle for a persisted row_id (fact, constraint, event, or decision ID). Bundle includes the entry, the containing signed epoch (Ed25519 + SLH-DSA hybrid signature envelope), an RFC 6962 Merkle inclusion proof, and the full epoch chain from genesis. Requires WORLD_MODEL_AUDIT_LOG=on at server startup; returns an error object when opt-in is off, when the row_id is not found, or when the entry is in the unclosed backlog.

v0.13 tamper-evident audit log. Return the current head state (last log entry seq, last closed epoch seq, unclosed-entry count) plus the full closed-epoch chain with hybrid signature envelopes. Compliance auditors call this periodically to verify no operator misbehavior has occurred since the last check. Requires WORLD_MODEL_AUDIT_LOG=on at server startup.