Agent Claude Code
Re-validates harness compatibility findings against current files and their cited sources, repairs mechanical drift at the canonical source, regenerates adapters, and hands every decision to a person.
Agent Claude Code
Re-validates harness compatibility findings against current files and their cited sources, repairs mechanical drift at the canonical source, regenerates adapters, and hands every decision to a person.
Agent Claude Code
Compares a converted Markdown file with its source PDF across seven fidelity dimensions and returns rated findings without editing either file.
Agent Claude Code
Re-validates each PDF conversion finding against the source and the current Markdown, restores confirmed gaps from the source, and records false positives and uncertain repairs.
Agent Claude Code
Converts PDF files to verbatim Markdown: text PDFs via pdftotext, image-only PDFs via OCR (tesseract), diagrams to Mermaid, and large files in 50-page chunks. By default it writes the .md beside the PDF under the same name.
Agent Claude Code
Audits a complete plan draft against the plan specification and returns criticality-rated findings to the plan quality gate, without modifying anything it audits.
Agent Claude Code
Audits finished plan execution in fixed order and returns the terminal verdict that permits or blocks archival.
Agent Claude Code
Executes Plan Propagation on a frozen plan quality ledger, re-validating each row against the current plan, repairing only what the plan's own decisions settle, and leaving every policy choice to the plan's owner.
Agent Claude Code
Authors a complete formal plan from an authorized request or groomed brief, returns every open decision to the root for grilling, and repairs its own draft within the declared budget.
Agent Claude Code
Checks one pinned change for the pr-review family by coordinating one review pass: after the lens checkers report, it deduplicates, re-categorizes, filters, verifies, and rates raw findings for criticality, then publishes the one review bound to the pinned head, editing no file.
Agent Claude Code
Reviews one pinned change for the documentation discipline, judging substantive completeness, clarity, mode fit, drift from the code, accessibility, and whether the change description matches the diff, and returns anchored findings.
Agent Claude Code
Executes PR Review Propagation on a frozen review ledger, answering each blocking row on one change with a fix, a reasoned reject, or a deferral, tagging each answer's cause, and committing fixes only to the change's own branch.
Agent Claude Code
Reviews one pinned change for the governance discipline, checking mechanical conformance to rules the repository documents, such as naming, structure, and required files and sections, and returns anchored findings.
Agent Claude Code
Reviews one pinned change for the instruction currency discipline, finding toolchain, dependency-manager, environment, or pipeline changes the agent instruction files no longer describe, and filler that adds no rule.
Agent Claude Code
Reviews one pinned change for the test integrity discipline, finding tests that were loosened, disabled, or cut back, gamed coverage, and bug fixes that land without a regression test, and returns anchored findings.
Agent Claude Code
Reviews one pinned change for the correctness discipline, judging behaviour against domain intent and the acceptance criteria across normal, edge, and error cases, and returns anchored findings.
Agent Claude Code
Reviews one pinned change for the performance discipline, finding concrete or likely regressions, hot-path changes, complexity growth, and memory and I/O cost, and returns anchored findings to the review coordinator, the pr-review checker.
Agent Claude Code
Prepares one pinned review pass before fan-out by choosing its risk tier, route, and specialist set with reasons, reading settled thread outcomes, and assembling one shared brief, without reviewing the change.
Agent Claude Code
Reviews one pinned change for the security discipline, finding secrets in the change, injection, untrusted-input gaps, and unsafe filesystem or version-control operations, and returns anchored findings to the review coordinator, the pr-review checker.
Agent Claude Code
Reviews one pinned change for the type-soundness discipline, finding escape hatches that let code compile while defeating the type system, and returns anchored findings to the review coordinator, the pr-review checker.
Agent Claude Code needs its repo
Executes Phase 0 of a plan delivery checklist: uses HIPPO for dependency and toolchain convergence, then runs scoped baselines and resolves preexisting failures before plan work begins.
Agent Claude Code
Validates workflow documentation quality and compliance with workflow pattern convention.
Agent Claude Code
Applies validated fixes from workflow-checker audit reports. Re-validates before applying changes.
Agent Claude Code
Creates workflow documentation in repo-governance/workflows/ following workflow pattern convention.
Agent Claude Code
Audits a repository's rules as a whole for contradictions across levels, inaccurate references, inconsistent terms and strengths, missing traceability, and duplicated bodies, and returns rated findings without editing.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: