A command that audits whether a repository's two coding-agent configuration trees, .claude/ and .github/, stay in sync. It compares mirrored instructions, skills, agents, registries, model settings, and configuration cost warnings.

Use it to run the repository audit, inspect only the paths reported as affected, choose the correct canonical version, and apply mechanical fixes when the report calls for them.

It identifies configuration drift so agents receive consistent guidance across both environments.

How RorroRojas3/awesome-claude-copilot configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to RorroRojas3/awesome-claude-copilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/RorroRojas3/awesome-claude-copilot/main/.claude/commands/repo-audit.md

Clone the repo

git clone --depth 1 https://github.com/RorroRojas3/awesome-claude-copilot

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/rorrorojas3/awesome-claude-copilot/repo-audit/github.svg)](https://agentmods.dev/commands/rorrorojas3/awesome-claude-copilot/repo-audit)

Your own site

<a href="https://agentmods.dev/commands/rorrorojas3/awesome-claude-copilot/repo-audit"><img src="https://agentmods.dev/badge/commands/rorrorojas3/awesome-claude-copilot/repo-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/rorrorojas3/awesome-claude-copilot/repo-audit"><img src="https://agentmods.dev/badge/commands/rorrorojas3/awesome-claude-copilot/repo-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 836 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00026	$0.00836
Opus 5	$0.00013	$0.00418
Sonnet 5	$0.00005	$0.00167
Haiku 4.5	$0.00003	$0.00084

Measured 9d ago against content hash 90c0c71a07e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

repo-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/repo-audit.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit the two harness trees against each other: mirrored skills, rule/instruction twins, agent twins and their model parity, registry listings, and cost hygiene.

The deterministic work lives in scripts/repo-audit.mjs — it compares content hashes, frontmatter, and registries, and prints a JSON report. Your job is only to act on what it flags.

1. Run the audit

node scripts/repo-audit.mjs --json

Append --strict if the user passed it (warnings then also fail).

2. Branch on the exit code — it is the contract

0 — clean. Print the one-line summary (it already carries the warning count) and stop immediately. Do not read files, do not "double-check" the trees — the hashes already did. This is the routine path and it should cost close to nothing.
1 — the script itself failed (unreadable tree, parse crash). Report the error and stop. Fix nothing on the basis of a failed check.
10 — findings. Continue below.

3. Read only what the report names

affectedPaths is your entire read-set — do not audit beyond it. Per finding:

skills-mirror/differs — decide the canonical side: git status / git diff shows which side carries the uncommitted (newer) change; cp it over the other. If both sides are committed and differ, do not guess — present both versions to the user.
skills-mirror/missing-* — cp the file into the tree that lacks it (or confirm with the user that it should be deleted from both).
rules-parity/body-drift — reconcile the wording semantically and apply the same sentence to both files. The script's header documents which cross-reference spellings are intentional and already mapped.
rules-parity/glob-mismatch — make the sets equal; the Claude paths: list is the canonical order.
agent-twins/model-parity — align the model to the parity table in scripts/repo-audit.mjs, or — only with the user's explicit approval — record a documented override in its modelParityOverrides (and the README convention note).
registry/* — add or remove the registry line; never invent a description — lift it from the twin.
cost-hygiene/* (warnings) — propose narrowed globs or trims in your report; never apply them under --fix. They change behavior, not just parity, so a human decides.

Read the full file on GitHub · 49 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 49 lines · 26 tokens per session scan A 90c0c71a07e8

Subscribe to this mod's changes

repo-audit is a command published in the GitHub repository RorroRojas3/awesome-claude-copilot (0 stars, last pushed 14d ago), licensed MIT. It adds 26 tokens to every session and 836 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.

Building agents

awesome-claude-copilot: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

1. Run the audit

2. Branch on the exit code — it is the contract

3. Read only what the report names

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement