agentleFS
Sign inStart free
r-irber-irbe/proof-skills/skills/lean-retroactive-audit/SKILL.md

lean-retroactive-audit

Skill3 starsChanged 24 days agoApache-2.0View on GitHub

USE FOR: Apply the review council system retroactively to an existing large Lean 4 project. DO NOT USE FOR: building a new council (@lean-review-council). TRIGGERS: retroactive audit, council onboarding, existing project audit.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    STOP if the project is new — delegate to @lean-specification to start from scratch.

    line 50
  2. Distinctive:

    STOP if the audit reveals architectural blockers — request HITL strategy decision.

    line 51
  3. Very specific:

    STOP if scope drifts into per-proof review — delegate single-proof items to @lean-proof-review.

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Lean 4 Retroactive Audit

Systematic methodology for applying the 5-member review council, Zettelkasten, and specification framework to a large existing Lean 4 codebase that was developed before these systems were in place.

Routing

  • USE FOR: Apply the review council system retroactively to an existing large Lean 4 project. Use when onboarding an existing codebase to the council review framework. Covers module discovery, dependency analysis, incremental audit scheduling, baseline establishment, gap analysis, and the catch-up RALPH cycle for bringing an existing project to full review coverage.
  • DO NOT USE FOR: building a new council (use @lean-review-council); single proof review (use @lean-proof-review); RETRO methodology (use @lean-retro-methodology).
  • TRIGGERS: retroactive audit, council onboarding, existing project audit, legacy Lean review.

Workflow

  1. Survey the existing project: count theorems, sorries, native_decide, axiom totals, council coverage gaps.
  2. Pick the audit playbook from the body matching the project scale (Solo / Small / Medium / Large).
  3. Execute the audit; produce a per-module readiness report with sequencing for council onboarding.
  4. Hand off: to @lean-review-council for the first council session, to @lean-retro-methodology for RETRO, to @lean-zettelkasten.

Recovery & STOP

  • STOP if the project is new — delegate to @lean-specification to start from scratch.
  • STOP if the audit reveals architectural blockers — request HITL strategy decision.
  • STOP if scope drifts into per-proof review — delegate single-proof items to @lean-proof-review.

Handoffs

  • Predecessors: agent:gateway, skill:lean-research.
  • Successors: skill:lean-review-council, skill:lean-retro-methodology, skill:lean-zettelkasten.

Detailed reference

Full content for lean-retroactive-audit lives in references/lean-retroactive-audit-handbook.md. Load that file when the skill is convened; the SKILL.md only carries the dispatch contract and the parts index.

SectionTopic
Part 1The Retroactive Challenge
Part 2Phase 0: Discovery
Part 3Phase 1: Baseline Establishment
Part 4Phase 2: Incremental Deep Audit
Part 5Phase 3: Gap Analysis and Extension
Part 6Phase 4: Steady-State Transition
Part 7Parallel Audit Dispatch

See also

  • ../../references/lean-retroactive-audit-handbook.md — Full handbook (extracted from this skill)
  • ../lean-review-council/SKILL.md — Successor
  • ../lean-retro-methodology/SKILL.md — Successor
  • ../lean-zettelkasten/SKILL.md — Successor

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free