A project scanner that finds issues and automatically fixes a limited set of safe problems, such as debugger statements and logging calls left in code.

Use it to scan a project for fixable debugging or placeholder problems, remove safe leftover debug code, and review issues such as hardcoded local URLs, secrets, or broken links.

It removes routine cleanup work while leaving issues that need human judgment clearly identified. It also rescans the project to check the result.

sniff-fix — Skill for Claude Code by Aboudjem: A project scanner that finds issues and automatically fixes…

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 skills/aboudjem/sniff/sniff-fix

Any agent

npx skills add Aboudjem/sniff --skill sniff-fix

Clone the repo

git clone --depth 1 https://github.com/Aboudjem/sniff

Made for: Claude Code.

Or install sniff, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

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/aboudjem/sniff/sniff-fix.svg)](https://agentmods.dev/skills/aboudjem/sniff/sniff-fix)

Your own site

<a href="https://agentmods.dev/skills/aboudjem/sniff/sniff-fix"><img src="https://agentmods.dev/badge/skills/aboudjem/sniff/sniff-fix.svg" alt="Measured on agentmods" height="20"></a>

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 451 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.

Model	Per session	Once invoked
Fable 5.1	$0.00031	$0.00451
Opus 5	$0.00015	$0.00226
Sonnet 5	$0.00006	$0.00090
Haiku 4.5	$0.00003	$0.00045

Measured 2d ago against content hash 164a2b640287, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sniff-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.

skills/sniff-fix/SKILL.md · 48 lines

What it actually says

/sniff-fix - Scan and fix issues

Scan the project, then automatically fix safe issues.

This skill is invoked by the sniff skill's own flow, not on its own. The user-invocable: false frontmatter key is honored by Claude Code only, so in other agents this file may show up as a standalone command; treat it as a step inside a sniff run rather than an entry point.

What to do

Use the unified sniff MCP tool with mode: "scan" and the project's rootDir to get all findings. If the unified tool is not available, use legacy sniff_scan.
For each finding, fix it if safe:
- debug-debugger: Remove the debugger; line
- debug-console-log: Remove console.log/debug/info lines
- placeholder-lorem: Flag to user (needs manual replacement)
- hardcoded-localhost: Suggest environment variable
- api-hardcoded-secret: Remove the secret and suggest env var
Do NOT auto-fix without telling the user what you're changing
After fixing, re-run unified sniff with mode: "scan" to verify issues are resolved

Example

User: /sniff-fix
You: I'll scan and fix what I can.

Found 8 issues. Auto-fixing 4:

- Removed `debugger` from src/handler.ts:42
- Removed `console.log` from src/api.ts:8
- Removed `console.log` from src/api.ts:15
- Removed `console.debug` from src/utils.ts:3

4 issues need manual attention:
- src/config.ts:8 - Hardcoded localhost URL (replace with env var)
- README.md:28 - Broken link to ./missing-guide.md
- ...

Re-scanning... 4 issues remaining (down from 8).

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.

2d ago Changed · +2 lines 164a2b640287
6d ago First seen · 46 lines · 31 tokens per session scan A 091fec57f468

Subscribe to this mod's changes

sniff-fix is a skill published in the GitHub repository Aboudjem/sniff (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 31 tokens to every session and 451 once invoked, about $0.0002 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.

Debugging Testing accessibility mcp playwright qa visual-regression

playwright-e2e-testing

Production-grade Playwright end-to-end testing skill for AI coding agents. Provides specialized guidance for writing, debugging, and maintaining Playwright tests in TypeScript, JavaScript, and Python. Covers the full testing lifecycle: test structure and architecture (Page Object Model, fixtures, custom matchers)…

JPeetz/agent-skills · 316 tokens

testing-e2e

End-to-end testing patterns with Playwright — page objects, AI agent testing, visual regression, accessibility testing with axe-core, and CI integration. Use when writing E2E tests, setting up Playwright, implementing visual regression, or testing accessibility.

yonatangross/orchestkit · 55 tokens

hatch3r-browser-verify

Opt-in browser verification skill — spec-run-first Playwright verification (assertions execute in the runner, agent reads only failures), axe-core a11y audits, toHaveScreenshot() regression diffs, E2E test scaffolds, and snapshot-mode exploratory driving. Default ON for UI-affecting agent invocations; disable globally…

hatch3r/hatch3r · 83 tokens

sniff-fix