What is gsd-audit-fix?

An automated review-and-repair workflow that finds issues, classifies them, fixes them, runs tests, and commits the changes.

Use it to audit a codebase, correct detected problems, check the result with tests, and create a commit.

It combines issue discovery and repair into one process instead of leaving fixes and verification as separate manual steps.

gsd-audit-fix — Skill for Claude Code by coco-research/coco

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.

Any agent

npx skills add coco-research/coco --skill gsd-audit-fix

Clone the repo

git clone --depth 1 https://github.com/coco-research/coco

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/skills/coco-research/coco/gsd-audit-fix/github.svg)](https://agentmods.dev/skills/coco-research/coco/gsd-audit-fix)

Your own site

<a href="https://agentmods.dev/skills/coco-research/coco/gsd-audit-fix"><img src="https://agentmods.dev/badge/skills/coco-research/coco/gsd-audit-fix/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/skills/coco-research/coco/gsd-audit-fix"><img src="https://agentmods.dev/badge/skills/coco-research/coco/gsd-audit-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 308 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	$0.00060	$0.00308
Opus 5.5	$0.00024	$0.00123
Sonnet 5.5	$0.00012	$0.00062
Haiku 4.5	$0.00006	$0.00031

Measured 1mo ago against content hash 9e0f6645d2fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gsd-audit-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 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.

systems/gsd/skills/gsd-audit-fix/SKILL.md · 34 lines

What it actually says

Flags:

--max N — maximum findings to fix (default: 5)
--severity high|medium|all — minimum severity to process (default: medium)
--dry-run — classify findings without fixing (shows classification table)
--source <audit> — which audit to run (default: audit-uat)

<execution_context> @$HOME/.claude/get-shit-done/workflows/audit-fix.md </execution_context>

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 Changed · +35 tokens per session 9e0f6645d2fd
2mo ago First seen · 34 lines · 25 tokens per session scan A 6e361a2bdb7d

Subscribe to this mod's changes

gsd-audit-fix is a skill published in the GitHub repository coco-research/coco (785 stars, last pushed yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 308 once invoked, about $0.0002 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 2026-09-03.

Claude Code Commits Debugging Git and workflow agent-skills agents-md ai ai-agents codex

gsd-audit-fix next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gsd-audit-fixcoco-research/coco	Skill	785	yesterday	Apache-2.0	A	60	Claude Code
git-advanced-workflowswshobson/agents	Skill	42k	yesterday	MIT	A	54	Claude Code
enable-check-includes-strictchromium/chromium	Skill	25k	yesterday	BSD-3-Clause	A	70	Claude Code, Codex
resolve-publishomnigent-ai/omnigent	Skill	11k	yesterday	Apache-2.0	A	21	Claude Code, Codex
gsd-audit-fixopen-gsd/gsd-core	Skill	11k	yesterday	MIT	A	25	Claude Code
fix-issueyonatangross/orchestkit	Skill	299	yesterday	MIT	A	45	Claude Code
git-worktree-precommit-hook-flutter-failuredivinevideo/divine-mobile	Skill	264	yesterday	MPL-2.0	A	153	Claude Code, Codex