A command that runs a codebase audit and records observed gaps in Hunch, an engineering-memory system. It stores the evidence, affected files or symbols, severity, and review status without changing the code.

Checking a codebase with searches, queries, or scripts; recording real gaps; linking gaps to violated rules; and reporting what was checked, what was clean, and what remains unverified.

It prevents audit findings from being based on assumptions and preserves the exact evidence behind each finding. It also makes repeatable checks easier to verify later.

How davesheffer/hunch configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to davesheffer/hunch. 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/davesheffer/hunch/main/.claude/commands/audit.md

Clone the repo

git clone --depth 1 https://github.com/davesheffer/hunch

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/davesheffer/hunch/audit/github.svg)](https://agentmods.dev/commands/davesheffer/hunch/audit)

Your own site

<a href="https://agentmods.dev/commands/davesheffer/hunch/audit"><img src="https://agentmods.dev/badge/commands/davesheffer/hunch/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/davesheffer/hunch/audit"><img src="https://agentmods.dev/badge/commands/davesheffer/hunch/audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 273 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	$0.00022	$0.00273
Opus 5.5	$0.00009	$0.00109
Sonnet 5.5	$0.00004	$0.00055
Haiku 4.5	$0.00002	$0.00027

Measured 1mo ago against content hash cbad55e25d6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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/audit.md · 14 lines

What it actually says

Audit $ARGUMENTS and record what you find into Hunch's graph.

Run the actual check (query/grep/script) — a finding needs EVIDENCE: the exact command you ran plus representative output. Never record a finding you didn't observe.
For each REAL gap: hunch_record_finding with title, observation, evidence, affected_files/affected_symbols, severity. It grounds future edits to those files automatically.
If the gap violates an existing invariant, link it via violates_constraint. If the RULE itself is unrecorded, capture the rule FIRST (hunch_record_correction), then link it.
If the audit is re-runnable, capture the procedure as a runbook and set method to its rb_* id — that makes the finding re-verifiable, not folklore.
Triage with me inline: open (default) / accepted-risk / scheduled. NEVER mark resolved without the fixing commit (resolved_commit).
Report: findings recorded (ids), what was checked and came back clean, and what stays unverified.

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.

1mo ago First seen · 14 lines · 22 tokens per session scan A cbad55e25d6a

Subscribe to this mod's changes

audit is a command published in the GitHub repository davesheffer/hunch (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 22 tokens to every session and 273 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

Code review ai-coding code-governance coding-agents developer-tools engineering-memory

hunch: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

audit-agents-skills

review

advanced-code-review-context

code-review-give

review-design-verify

argos