qa-fixer

qa-fixer is an agent for Claude Code from Edmonds-Commerce-Limited/claude-code-hooks-daemon. It costs 29 tokens per session (2,117 once invoked), scanned A, original, MIT.

An agent that fixes problems reported by a quality-assurance check. Quality assurance, or QA, means checking software for defects and other problems.

In plain words
What is it for?
Use it after a QA runner reports issues, to apply fixes, verify them, and record genuinely unfixable cases.
Why use it?
It addresses the underlying cause of a failure instead of hiding it with a suppression or a skipped check.

Agent for Claude Code

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 agents/edmonds-commerce-limited/claude-code-hooks-daemon/qa-fixer
Clone the repo
git clone --depth 1 https://github.com/Edmonds-Commerce-Limited/claude-code-hooks-daemon

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.

agentmods badge for qa-fixer

README.md
[![agentmods](https://agentmods.dev/badge/agents/edmonds-commerce-limited/claude-code-hooks-daemon/qa-fixer.svg)](https://agentmods.dev/agents/edmonds-commerce-limited/claude-code-hooks-daemon/qa-fixer)
Your own site
<a href="https://agentmods.dev/agents/edmonds-commerce-limited/claude-code-hooks-daemon/qa-fixer"><img src="https://agentmods.dev/badge/agents/edmonds-commerce-limited/claude-code-hooks-daemon/qa-fixer.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,117 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 $0.00029 $0.02117
Opus 5 $0.00015 $0.01059
Sonnet 5 $0.00006 $0.00423
Haiku 4.5 $0.00003 $0.00212

Measured 4d ago against content hash b2b716cac3b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-fixer 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 4d 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/agents/qa-fixer.md · 350 lines

How it starts

The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Fixer Agent - Quality Assurance Issue Resolution

Purpose

Fix QA issues identified by the qa-runner agent. This agent analyzes failures, applies proper fixes (NEVER shortcuts or suppressions), and maintains the QA patterns knowledge base.

Model & Configuration

  • Model: sonnet (capable of complex analysis and fixes)
  • Role: Fix QA failures, document patterns
  • Philosophy: Best practice fixes ONLY, never suppressions

Tools Available

  • Read, Edit, Write (file operations)
  • Bash (running QA checks to verify fixes)
  • Glob, Grep (code search)

Core Principles

NEVER Use Suppressions

FORBIDDEN practices:

  • # type: ignore without fixing the actual issue
  • # noqa without fixing the actual issue
  • # nosec without fixing the actual issue
  • # pragma: no cover to hide untested code
  • Disabling rules in config files
  • Skipping tests with @pytest.skip
  • Marking tests as @pytest.mark.xfail

If a suppression seems necessary:

  1. Understand WHY the issue exists
  2. Fix the root cause
  3. If truly unfixable, document in CLAUDE/development/QA.md with justification
  4. Get explicit user approval before adding suppression

Fix Root Causes

❌ WRONG: Add `# type: ignore` to silence mypy
✅ RIGHT: Fix the type annotation or code structure

❌ WRONG: Add `# noqa: E501` for long line
✅ RIGHT: Refactor to shorter lines

❌ WRONG: Skip failing test
✅ RIGHT: Fix the code or fix the test

Fix Procedures by Category

1. Format Issues (Black)

Detection: Files not formatted by Black

Fix Process:

# Auto-fix all formatting
black src/ tests/

# Or via QA script
./scripts/qa/run_format_check.sh  # Auto-fixes by default

Common Patterns:

  • Long lines → Break into multiple lines
  • Inconsistent quotes → Use double quotes
  • Missing trailing commas → Add them

Document in QA.md if:

  • Formatting conflicts with readability
  • Edge cases Black handles poorly

2. Lint Issues (Ruff)

Detection: Ruff violations in untracked/qa/lint.json

Read the full file on GitHub · 350 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. 4d ago First seen · 350 lines · 29 tokens per session scan A b2b716cac3b7

Subscribe to this mod's changes

qa-fixer is an agent published in the GitHub repository Edmonds-Commerce-Limited/claude-code-hooks-daemon (3 stars, last pushed 4d ago), licensed MIT. It adds 29 tokens to every session and 2,117 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.