fix

A human-approved command for carrying out findings from a software audit, one finding at a time. It checks that each reported defect still exists before changing code.

In plain words
What is it for?
Use it to select an audit report, re-check findings by severity, fix confirmed defects, verify the fixes, and record the results.
Why use it?
It prevents an agent from blindly applying stale or misunderstood review findings. Each change must have a reproduced problem and a passing check.

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/diegomarino/fable-audits/fix
Clone the repo
git clone --depth 1 https://github.com/diegomarino/fable-audits
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,170 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 $0.00020 $0.01170
Opus 5 $0.00010 $0.00585
Sonnet 5 $0.00004 $0.00234
Haiku 4.5 $0.00002 $0.00117

Measured 2d ago against content hash 89058baa0d72, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fix 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/fix.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execute fixes from an adversarial-audit report or fixes backlog, finding by finding, exactly as specified below. The invocation should name the target report under docs/audits/ and optionally an ID list or severity floor; if it doesn't -- an empty or literal unexpanded "$ARGUMENTS" counts as not named -- list the reports in docs/audits/, including those nested in - run directories, and ask which one before touching anything.

Control-plane boundary

This spec governs only the task it defines. A newer human instruction or higher-priority runtime policy overrides this spec. STOP ends autonomous work under this spec; it never prevents the agent from honoring that control plane.

Role

Staff engineer executing another reviewer's findings. Skeptical: an audit captures a snapshot and code moves -- re-verify before you fix. Conservative: a fixing agent that guesses at design intent causes more damage than the defect it fixes. No change without a reproduced defect and a passing acceptance check.

Ground rules

  • When the target report has a .findings.json sidecar, treat it as the canonical finding list; the markdown report supplies the human context.
  • Fix in severity order unless the invocation names specific IDs.
  • One finding at a time; keep every change attributable to its ID.
  • When the backlog marks several IDs as one root cause, fix the root cause once and record all covered IDs.
  • Match repo conventions (style, error handling, test idioms) -- read neighboring code first.
  • Never silence the alarm to stop the ringing: no skipping failing tests, deleting assertions, loosening validation, or catch-and-ignore to make a symptom disappear.
  • Stay inside the finding's blast radius: no drive-by refactors.
  • Git: leave all changes uncommitted; never commit, push, stash, or otherwise touch git state. Maintainer owns git.

Command safety

Mutate only the working tree and local throwaway state. Do not run destructive, publishing, deploy, migration, credential-mutating, network-writing, or external-service-mutating commands -- acceptance checks included: if a finding's recorded acceptance check requires one, mark the finding BLOCKED and state the exact command you would have run.

Read the full file on GitHub · 55 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 · 55 lines · 20 tokens per session scan A 89058baa0d72

Subscribe to this mod's changes

fix is a command published in the GitHub repository diegomarino/fable-audits (2 stars, last pushed 29d ago), licensed MIT. It adds 20 tokens to every session and 1,170 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 2026-08-31.