Agent skill

Audit Repository Consistency

by converge-ai-labs in converge-ai-labs/agent-foundation

Audit a repository or revision range for spec-code gaps, inconsistent shared concepts, semantic duplication, and removable code.

Apache-2.0Auto-check passedDevelopment

Install Audit Repository Consistency

skills CLI
$ npx skills add converge-ai-labs/agent-foundation --skill audit-repository-consistency -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install converge-ai-labs/agent-foundation audit-repository-consistency --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/converge-ai-labs/agent-foundation.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/audit-repository-consistency .claude/skills/audit-repository-consistency && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
audit-repository-consistency
GitHub stars
173
Token cost
~1.8k tokens
SKILL.md length
863 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

Audit a repository or revision range for spec-code gaps, inconsistent shared concepts, semantic duplication, and removable code.

  • Works in 5 steps: Static references, aliases, exports, and… → Registries, decorators, reflection,… → CLI, environment, deployment, scheduled,… → …
  • Repository consistency
  • SKILL.md covers Scope and Evidence, Resolve the Audit Basis, Trace the Relevant System and Audit Passes, plus 1 more section
  • Calls rg and git

What it does

Audit Repository Consistency is an agent skill from converge-ai-labs/agent-foundation. Audit a repository or revision range for spec-code gaps, inconsistent shared concepts, semantic duplication, and removable code. Use for repository consistency or architecture-conformance reviews; report evidence-backed findings and remediate only when requested.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development. The repository describes itself as: a13n - An open-source library and self-hosted platform for building and running your own agent systems—with managed agents, memory, sandboxes, computer use, and durable… The licence is Apache-2.0.

When your agent uses it

  • Repository consistency
  • Architecture-conformance reviews
  • Report evidence-backed findings and remediate only when requested

Example prompts

  • “/audit-repository-consistency”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Static references, aliases, exports, and string keys.
  2. Registries, decorators, reflection, dynamic imports, plugin discovery, and import side effects.
  3. CLI, environment, deployment, scheduled, serialization, persistence, and external entry points.
  4. Generators, manifests, packaging, builds, and release automation.
  5. Deprecation promises, old clients, compatibility layers, and migration history.

What it can do on your machine

Read from SKILL.md and the folder at commit b2b8a3e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • rg
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Audit Repository Consistency loads about 1.8k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 863 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from converge-ai-labs/agent-foundation at commit b2b8a3e, republished under its Apache-2.0 licence (© converge-ai-labs). 863 words, ~1,777 tokens.

Download SKILL.mdSave it as .claude/skills/audit-repository-consistency/SKILL.md (or your agent's skills folder).
name
audit-repository-consistency
description
Audit a repository or revision range for spec-code gaps, inconsistent shared concepts, semantic duplication, and removable code. Use for repository consistency or architecture-conformance reviews; report evidence-backed findings and remediate only when requested.

Repository Consistency Audit

Determine whether accepted contracts match actual behavior, shared concepts have consistent owners, and retained implementation paths still serve a purpose. Prefer consequential, proven findings over search matches.

Scope and Evidence

Follow the repository's AGENTS.md and contribution rules. Read the engineering standards and owning specification sections for the surfaces under review; use spec/README.md to locate owners. Reuse documents already read.

Keep audits read-only unless remediation is requested. Accepted specifications define intended behavior; code and tests establish actual behavior. Do not copy implementation drift into a specification to make the mismatch disappear. Private implementation details need a specification only when they affect observable behavior, ownership, security, or compatibility.

Resolve the Audit Basis

Identify the target snapshot, optional baseline, and requested surfaces before analysis:

  • Default to the current worktree, including staged, unstaged, and relevant untracked changes. Record the full HEAD ID and whether local changes are included. An explicit revision or HEAD request excludes local changes.
  • A whole-project or full request has no baseline. A request limited to a feature, directory, or file stays within that scope, including directly affected owners and consumers.
  • For a branch or change review without an explicit base, inspect Git status, the repository default/integration branch, merge base, and diff summary. Use the meaningful base found there and state the choice; a tracking ref that merely mirrors the feature branch is not a useful base.
  • Resolve supplied revisions to full commit IDs. Interpret “against a branch/ref” as its merge base with the target unless an exact snapshot comparison is requested. Use an explicit ancestor commit directly.
  • Ask a focused question only if unresolved topology, missing refs, or multiple plausible targets/bases would materially change coverage. For a non-ancestor explicit commit without comparison semantics, clarify exact comparison versus merge base.

State the resolved basis and proceed when the request and Git evidence establish it. Do not require confirmation just because a default was used, and do not infer a previous audit or maintain checkpoints.

Trace the Relevant System

Inventory with rg --files or git ls-files; locate owning specs, public entry points, schemas, persistence, generators, tests, and automation. Mark generated, vendored, fixture, cache, and migration-history paths so they are assessed through their owners.

For incremental reviews, read the aggregate diff with renames/deletions, then relevant commits when intent is unclear. Extract changed concepts and trace affected consumers beyond changed lines. For a full audit, start with specification indexes, public and durable boundaries, and shared infrastructure.

Follow each material concept through applicable stages:

text
specification -> definition/generation -> validation/persistence
              -> transport/SDK/UI -> observability/tests

Batch related searches and deep-read plausible owning paths. Use existing non-mutating checks to test candidates; do not install audit-only dependencies without authorization.

Audit Passes

Specification and implementation

Trace both directions: accepted entities, operations, defaults, states, authority, compatibility, and failure rules into code; public or durable behavior back to its owning contract. Compare semantics, including ordering, cancellation, retries, completion, and unknown outcomes.

Classify gaps as stale specification, implementation drift, incomplete implementation, missing accepted contract, intentional private detail, or unresolved design. Establish which authority should change before recommending remediation.

Show full SKILL.md (364 more words)Show less
Consistency and duplication

Look for competing policies or representations of IDs, pagination, time, versions, errors, state transitions, configuration, schemas, authorization, transactions, logging, and redaction.

Recommend a canonical owner when definitions encode the same policy and must evolve together. Preserve deliberate isolation across packages, releases, languages, runtimes, and security boundaries. Boundary adapters, compatibility layers, and defense-in-depth checks may legitimately repeat logic; a few similar lines do not justify an abstraction. Prefer generation over runtime coupling for shared cross-language wire contracts.

Invalid and removable code

Check unreachable or ineffective paths, orphaned registrations/assets/jobs, unused dependencies, expired flags, superseded helpers, and completed cutovers.

Before calling anything removable, verify:

  1. Static references, aliases, exports, and string keys.
  2. Registries, decorators, reflection, dynamic imports, plugin discovery, and import side effects.
  3. CLI, environment, deployment, scheduled, serialization, persistence, and external entry points.
  4. Generators, manifests, packaging, builds, and release automation.
  5. Deprecation promises, old clients, compatibility layers, and migration history.

Classify candidates as confirmed removable, redundant and consolidatable, obsolete but compatibility-bound, or unproven. Age, missing tests, TODOs, and zero-result searches are not removal proof.

Validate and Report

For each candidate, read its complete owning contract and implementation path, trace alternate and cross-language consumers, and inspect relevant tests. Try to falsify it by looking for intentional isolation or compatibility requirements. Run the narrowest useful non-mutating checks; for review-only work, avoid formatting gates that rewrite the worktree.

Report actionable findings by severity, with a short statement of target/full commit ID, baseline/full commit ID or full audit, and worktree scope. Give each finding:

  • A stable ID, category, severity, and confidence.
  • Exact specification and implementation evidence with file paths and lines.
  • Actual versus required behavior and a concrete consequence.
  • The responsible owner and smallest coherent fix.
  • Removal proof, compatibility constraints, or unresolved decisions where relevant.

Include commands/results and coverage limitations. Keep unproven concerns separate from defects; never claim full coverage from sampling. If no actionable findings remain, say what was examined.

When fixes are requested, implement supported remediations and relevant tests. Use the repository's spec-writing skill for accepted specification changes. An unresolved design decision blocks only the affected remediation; continue independent authorized work. GitHub posting and other external mutations remain subject to the user's authorization.

© converge-ai-labs, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/audit-repository-consistency of converge-ai-labs/agent-foundation.

Open the folder on GitHubat commit b2b8a3e

Compare with similar skills

Audit Repository Consistency next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Audit Repository Consistency compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Audit Repository Consistency this skillconverge-ai-labs/agent-foundation173—~1.8kAutomated safety check: PassApache-2.0
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k4 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 58 repos~726 tokens
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 4 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from converge-ai-labs/agent-foundation

  • Spec Writing

    converge-ai-labs/agent-foundation

    Author, review, or reorganize accepted technical contracts under spec/, including domain models, lifecycles, APIs, protocols, ownership, security, and compatibility.

    173 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Worktree PR

    converge-ai-labs/agent-foundation

    Start a task in a Git worktree under .worktrees/ from freshly fetched origin/main, implement and validate it, then use commit-push-pr to open or update a PR.

    173 GitHub stars~1.2k tokensUpdated today
    Auto-check: notes
  • Commit Push PR

    converge-ai-labs/agent-foundation

    Prepare focused commits, push branches, and create or update GitHub pull requests when requested.

    173 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Uiux Polish

    converge-ai-labs/agent-foundation

    Build and refine frontend pages and interactions with strong visual taste, proactive polish, and lightweight iteration.

    173 GitHub stars~580 tokensUpdated today
    Auto-check passed

Categories

Questions about Audit Repository Consistency

What does Audit Repository Consistency do?

Audit a repository or revision range for spec-code gaps, inconsistent shared concepts, semantic duplication, and removable code. Audit Repository Consistency is an agent skill from converge-ai-labs/agent-foundation. Audit a repository or revision range for spec-code gaps, inconsistent shared concepts, semantic duplication, and removable code.

When should I use Audit Repository Consistency?

Audit Repository Consistency fits situations like: repository consistency; architecture-conformance reviews; report evidence-backed findings and remediate only when requested.

How do I install Audit Repository Consistency in Claude Code?

Run `npx skills add converge-ai-labs/agent-foundation --skill audit-repository-consistency -a claude-code`. Or copy the skill folder (.agents/skills/audit-repository-consistency in converge-ai-labs/agent-foundation) into .claude/skills/audit-repository-consistency in your project. Claude Code loads it when a task matches its description.

How do I install Audit Repository Consistency in Codex?

Run `npx skills add converge-ai-labs/agent-foundation --skill audit-repository-consistency -a codex`. Or copy the skill folder (.agents/skills/audit-repository-consistency in converge-ai-labs/agent-foundation) into .agents/skills/audit-repository-consistency in your project. Codex loads it when a task matches its description.

Can I use Audit Repository Consistency in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add converge-ai-labs/agent-foundation --skill audit-repository-consistency -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audit-repository-consistency, .gemini/skills/audit-repository-consistency, .github/skills/audit-repository-consistency and .opencode/skills/audit-repository-consistency in your project.

What does Audit Repository Consistency need to run?

Going by SKILL.md and its folder, Audit Repository Consistency needs the command-line tools its instructions call (rg and git).

Does Audit Repository Consistency access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Audit Repository Consistency safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Audit Repository Consistency use?

Audit Repository Consistency is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Audit Repository Consistency use?

About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Audit Repository Consistency?

Skills that share tags, products or a category with Audit Repository Consistency: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audit Repository Consistency?

converge-ai-labs (a GitHub organization) maintains it in converge-ai-labs/agent-foundation, which has 173 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 11, 2026.

Source: converge-ai-labs/agent-foundation on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.