audit-repository-consistency
Skill1.3k starsChanged 4 days agoApache-2.0View on GitHub
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.
Adopted by
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Who's talking about converge-ai-labs/agent-foundation
- converge-ai-labs/a13n-sdk-typescript“chore(contract): update Service snapshot to 351d598a2315”GitHub · Nov 5, 2026
- converge-ai-labs/a13n-sdk-rust“chore(contract): update Service snapshot to 330c4af4e12a”GitHub · Nov 5, 2026
- converge-ai-labs/a13n-sdk-go“chore(contract): update Service snapshot to 351d598a2315”GitHub · Nov 5, 2026
- converge-ai-labs/a13n-sdk-python“chore(contract): update Service snapshot to e9ee726112f5”GitHub · Nov 5, 2026
- converge-ai-labs/a13n-sdk-rust“feat(sdk)!: support Environment desktop control in Rust SDK and CLI”GitHub · Oct 29, 2026
The biggest 5 of 50 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 50
Talked about on GitHub (50 times).
On GitHub · 50
- Nov 5, 2026chore(contract): update Service snapshot to 351d598a2315 — converge-ai-labs/a13n-sdk-typescript0 reactions
- Nov 5, 2026chore(contract): update Service snapshot to 330c4af4e12a — converge-ai-labs/a13n-sdk-rust0 reactions
- Nov 5, 2026chore(contract): update Service snapshot to 351d598a2315 — converge-ai-labs/a13n-sdk-go0 reactions
- Nov 5, 2026chore(contract): update Service snapshot to e9ee726112f5 — converge-ai-labs/a13n-sdk-python0 reactions
- Oct 29, 2026feat(sdk)!: support Environment desktop control in Rust SDK and CLI — converge-ai-labs/a13n-sdk-rust0 reactions
45 more on GitHub
- Oct 29, 2026feat(sdk)!: support Environment desktop control and current Service APIs — converge-ai-labs/a13n-sdk-typescript0 reactions
- Oct 29, 2026feat(sdk)!: support Environment desktop control and current Service APIs — converge-ai-labs/a13n-sdk-go0 reactions
- Oct 29, 2026feat(sdk)!: support Environment desktop control and current Service APIs — converge-ai-labs/a13n-sdk-python0 reactions
- Oct 19, 2026feat(sdk)!: support committed Apps and recover truncated SSE — converge-ai-labs/a13n-sdk-rust0 reactions
- Oct 19, 2026feat(sdk)!: support committed Apps and recover truncated SSE — converge-ai-labs/a13n-sdk-go0 reactions
- Oct 19, 2026feat(sdk)!: support committed Apps and recover truncated streams — converge-ai-labs/a13n-sdk-python0 reactions
- Oct 19, 2026feat(sdk)!: support committed Apps and paginated Run usage — converge-ai-labs/a13n-sdk-typescript0 reactions
- Oct 18, 2026Separate deferred-tool discovery from callability for reusable programs — pydantic/pydantic-ai0 reactions · 3 comments
- Oct 16, 2026feat(sdk): support desktop control, tool discovery and context usage — converge-ai-labs/a13n-sdk-rust0 reactions
- Oct 15, 2026feat(sdk): support desktop control and native tool discovery — converge-ai-labs/a13n-sdk-go0 reactions
- Oct 15, 2026feat(sdk): support desktop control, tool discovery and context usage — converge-ai-labs/a13n-sdk-python0 reactions
- Oct 15, 2026feat(sdk): support desktop control and native tool discovery — converge-ai-labs/a13n-sdk-typescript0 reactions
- Oct 15, 2026feat(streams)!: add native Session snapshots and update Items readback — converge-ai-labs/a13n-sdk-go0 reactions
- Oct 15, 2026feat(streams)!: add typed Session snapshots and update Items readback — converge-ai-labs/a13n-sdk-python0 reactions
- Oct 15, 2026feat(streams)!: add typed Session snapshots and update Items readback — converge-ai-labs/a13n-sdk-typescript0 reactions
- Oct 13, 2026feat(sdk): support shared memory spaces and computer contracts — converge-ai-labs/a13n-sdk-go0 reactions
- Oct 13, 2026feat(sdk): support shared memory spaces and run inspection — converge-ai-labs/a13n-sdk-rust0 reactions
- Oct 13, 2026feat(sdk): support Memory Spaces and execution diagnostics — converge-ai-labs/a13n-sdk-typescript0 reactions
- Oct 7, 2026feat(sdk)!: add Findings and preserve imported history order — converge-ai-labs/a13n-sdk-go0 reactions
- Oct 7, 2026feat(sdk)!: add Findings, saved content and message-author reads — converge-ai-labs/a13n-sdk-python0 reactions
- Oct 4, 2026feat(sdk): support ordinal Run display windows and continuation — converge-ai-labs/a13n-sdk-go0 reactions
- Oct 4, 2026feat(sdk): support paged Run display and sealed-history continuation — converge-ai-labs/a13n-sdk-python0 reactions
- Oct 4, 2026feat(sdk): expose ordinal Run display windows and nullable item metadata — converge-ai-labs/a13n-sdk-typescript0 reactions
- Sep 30, 2026🚨 自动扫描发现高危密钥 (2026-09-30) — butwedont/butwedont.github.io0 reactions
- Sep 18, 2026Add SDK-owned integration CI against pinned, main, and released Service targets — converge-ai-labs/a13n-sdk-python0 reactions
- Sep 17, 2026chore: update Service contract to 9d6ab5529b6d — converge-ai-labs/a13n-sdk-rust0 reactions · 1 comment
- Sep 17, 2026chore: update Service contract to 9d6ab5529b6d — converge-ai-labs/a13n-sdk-go0 reactions · 1 comment
- Sep 17, 2026chore: update Service contract to 9d6ab5529b6d — converge-ai-labs/a13n-sdk-python0 reactions · 1 comment
- Sep 17, 2026chore: update Service contract to d26ece6d8b23 — converge-ai-labs/a13n-sdk-rust0 reactions · 1 comment
- Sep 17, 2026chore: update Service contract to d26ece6d8b23 — converge-ai-labs/a13n-sdk-go0 reactions · 1 comment
- Sep 17, 2026chore: update Service contract to d26ece6d8b23 — converge-ai-labs/a13n-sdk-python0 reactions · 1 comment
- Sep 17, 2026chore: update Service contract to b271ada99701 — converge-ai-labs/a13n-sdk-python0 reactions · 1 comment
- Sep 17, 2026chore: update Service contract to b271ada99701 — converge-ai-labs/a13n-sdk-rust0 reactions · 1 comment
- Sep 17, 2026chore: update Service contract to b271ada99701 — converge-ai-labs/a13n-sdk-go0 reactions · 1 comment
- Sep 16, 2026chore: update Service contract to 8f60ca0fcfd9 — converge-ai-labs/a13n-sdk-go0 reactions · 1 comment
- Sep 16, 2026chore: update Service contract to 8f60ca0fcfd9 — converge-ai-labs/a13n-sdk-rust0 reactions · 1 comment
- Sep 16, 2026chore: update Service contract to 0e5501328a3c — converge-ai-labs/a13n-sdk-rust0 reactions · 1 comment
- Sep 16, 2026chore: update Service contract to 0e5501328a3c — converge-ai-labs/a13n-sdk-go0 reactions · 1 comment
- Sep 16, 2026chore: update Service contract to e00e21d89fcd — converge-ai-labs/a13n-sdk-go0 reactions · 1 comment
- Sep 16, 2026chore: update Service contract to e00e21d89fcd — converge-ai-labs/a13n-sdk-rust0 reactions · 1 comment
- Sep 16, 2026chore: update Service contract to 59cd7756419f — converge-ai-labs/a13n-sdk-go0 reactions · 1 comment
- Sep 16, 2026chore: update Service contract to 59cd7756419f — converge-ai-labs/a13n-sdk-rust0 reactions · 1 comment
- Sep 16, 2026chore: update Service contract to e1d37353fb43 — converge-ai-labs/a13n-sdk-rust0 reactions · 1 comment
- Sep 16, 2026chore: update Service contract to e1d37353fb43 — converge-ai-labs/a13n-sdk-go0 reactions · 1 comment
- Sep 16, 2026chore: update Service contract to 23339a58f40e — converge-ai-labs/a13n-sdk-rust0 reactions · 1 comment
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- commit-push-prSkill
- spec-writingSkill
- uiux-polishSkill
- worktree-prSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Follow the repository's AGENTS.md and contribution rules.
- Very specific: line 20
Default to the current worktree, including staged, unstaged, and relevant untracked changes.
- Distinctive: line 24
Ask a focused question only if unresolved topology, missing refs, or multiple plausible targets/bases would materially change coverage.
- Distinctive: line 34
Follow each material concept through applicable stages:
- Distinctive: line 53
Look for competing policies or representations of IDs, pagination, time, versions, errors, state transitions, configuration, schemas, …
- Very specific: line 59
Check unreachable or ineffective paths, orphaned registrations/assets/jobs, unused dependencies, expired flags, superseded helpers, and …
- Distinctive: line 61
Before calling anything removable, verify:
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.
Files
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
HEADID and whether local changes are included. An explicit revision orHEADrequest excludes local changes. - A whole-project or
fullrequest 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:
specification -> definition/generation -> validation/persistence
-> transport/SDK/UI -> observability/testsBatch 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.
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:
- Static references, aliases, exports, and string keys.
- Registries, decorators, reflection, dynamic imports, plugin discovery, and import side effects.
- CLI, environment, deployment, scheduled, serialization, persistence, and external entry points.
- Generators, manifests, packaging, builds, and release automation.
- 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.
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
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.

