auditor:patch

A verified proposal for fixing one confirmed security finding, delivered as a minimal Git patch rather than a change to the real project files.

In plain words
What is it for?
Use it to create a unified diff against the reviewed commit, apply it in a scratch worktree, and check that the finding's proof-of-concept no longer succeeds.
Why use it?
It lets you inspect and test a narrowly targeted fix while keeping the audited codebase unchanged.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/solanabr/auditor-skill/patch
Clone the repo
git clone --depth 1 https://github.com/solanabr/auditor-skill
Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,143 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00094 $0.01143
Opus 5 $0.00047 $0.00571
Sonnet 5 $0.00019 $0.00229
Haiku 4.5 $0.00009 $0.00114

Measured 2d ago against content hash d3a783764ed4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auditor:patch 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 2d 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.

commands/patch.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

auditor-skill — Patch Draft & Verification

Arguments: $ARGUMENTS

Produce a verified fix proposal for a confirmed finding. Read OUTPUT-RULES.md first (severity 1-10, Rule 5b) and the finding's block + its audit_<n>/poc/F-xxx harness (the executed exploit the fix must now defeat). The patch is a deliverable, not an application — the auditor never writes to the client's real tree; it stays read-only on the target and hands back a diff plus a verification record.

Steps

  1. Resolve the finding. Read the finding block from audit_<n>/REPORT.md, its context worksheet under worksheets/context/*, and its poc/F-xxx crate if /auditor:poc already ran. Pin the audited commit — the diff must apply against that commit, not HEAD.

  2. Spawn patch-engineer. It writes audit_<n>/patches/F-xxx.patch: a minimal, idiomatic unified diff that closes exactly the cited reachability/bound — no refactor, no drive-by cleanup, nothing beyond the one guard/bound the finding names. It obeys .claude/rules/{rust,anchor,pinocchio}.md: checked arithmetic (checked_add/checked_sub/…), stored canonical bumps (never recalculated), transfer_checked (not deprecated transfer), no unwrap()/expect() in program code, validated CPI targets. A cosmetic edit that does not move the Rule 5b bound is not a fix.

  3. Verify by execution (mandatory for [FIX-VERIFIED]). Apply the patch to a scratch git worktree (never the client checkout), rebuild, and re-run the finding's poc/F-xxx exploit. The exploit must now revert / fail on the patched build — the previously-succeeding vulnerable path is closed. Reading the diff is not verification; only an executed revert earns [FIX-VERIFIED]. If no executable PoC exists, the ceiling is [FIX-PROPOSED] (verified by re-derivation, not by execution).

  4. Mutation + blast-radius (optional). With --verify-with-mutation, run mewt mutation on the patched line(s) via Trail of Bits mutation-testing (references/orchestration/boundary-map.md) — an uncaught mutant on the fix means the guard is under-tested, so record it and do not overstate the verification. Always run a differential-review blast-radius check (Trail of Bits): apply the same diff-vs-behavior comparison to confirm the fix closes the exploit path and leaves every other path unchanged — a fix that breaks an adjacent instruction is [FIX-INSUFFICIENT].

Read the full file on GitHub · 40 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.

  1. 2d ago First seen · 40 lines · 94 tokens per session scan A d3a783764ed4

Subscribe to this mod's changes

auditor:patch is a command published in the GitHub repository solanabr/auditor-skill (50 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,143 once invoked, about $0.0005 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 2026-08-30.