Run every enabled DocGuard validator against the project's canonical docs. Returns status (PASS/WARN/FAIL), every finding once with its stable code and suggestion, each code's evidence once, nextStep, doc coverage, semantic-claim count, and per-validator status and counts. Pass detail "full" for the complete guard JSON contract (per-validator finding copies, the reportable subset, raw benchmark statistics per code).

Compute the project's CDD maturity score (0-100) with letter grade and per-category breakdown.

Explain a stable DocGuard finding code (e.g. STR001, ENV003): what it means, which validator emits it, and the inline suppression to use if it's a confirmed false positive.

Evaluate .docguard-evidence.json against bounded local sources. Returns explicit verified-within-scope, contradicted, stale, inconclusive, and unsupported states; verification applies only to each selected statement.

Extract the semantic claims in the project's canonical docs — documented numbers, limits, and enums — as a verification task list. Deterministic discovery, LLM judgment — the caller verifies each claim against the code.

Generate the commit-stamped compliance-evidence bundle: guard verdict per validator, findings grouped by stable code, CDD score, ALCOA+ data-integrity attributes, fix history, and a tamper-evident sha256 integrity hash. Evidence, not a gate — it reports state without failing.

Exact answer to "which documentation describes this file?": canonical doc lines that name it (with heading, anchor and section), AGENTS.md/CLAUDE.md/GEMINI.md lines, the @implements/@req IDs it declares, its @doc annotations, and doc sections whose covers= includes it with their review state. Deterministic, bounded, no model.

A document's headings (level, text, anchor, line range, bytes), docguard:section markers (id, source, pinned, covers), fact markers, marker issues, last-reviewed date and size — so an agent can read one section instead of the whole file.

Return one section's text, resolved by docguard:section id, then heading anchor, then exact heading text — or, with line, just the lines around one reference from docguard_docs_for_path (the cheapest read for a table row). Bounded: 8192 bytes by default, 32768 at most; a truncated result carries nextOffset. An ambiguous match fails with the candidates.

The same deterministic packet as docguard agent --task <text> --format json: current task-linked requirements, pointers to implementing code and tests, excerpts, and verification steps; abstains when relevance is weak.

Run guard and return only what needs fixing: failing/warning validators with their messages, structured findings, and suggested next actions — shaped for an agent to act on.