An automated quality loop that audits a project, checks whether findings are real, fixes high-priority issues, runs verification, and repeats until its stopping rules are met. It can audit security, performance, accessibility, and project instructions in parallel.

Use it to run repeated quality checks, validate findings, fix P0/P1 issues, verify tests, and stop after a target score or iteration limit; audit-only mode produces a report without fixes.

It reduces the back-and-forth of finding issues, filtering false alarms, applying fixes, and checking the result. Scoping the work to the current branch changes helps focus the loop on recent code.

qa-loop — Command for Claude Code by christopherlouet

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.

Clone the repo

git clone --depth 1 https://github.com/christopherlouet/claude-base

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/commands/christopherlouet/claude-base/qa-loop.svg)](https://agentmods.dev/commands/christopherlouet/claude-base/qa-loop)

Your own site

<a href="https://agentmods.dev/commands/christopherlouet/claude-base/qa-loop"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/qa-loop.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,209 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	$0.00000	$0.01209
Opus 5	$0.00000	$0.00605
Sonnet 5	$0.00000	$0.00242
Haiku 4.5	$0.00000	$0.00121

Measured 3d ago against content hash afa28097cbf3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

qa-loop 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 3d 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/commands/qa/qa-loop.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA-LOOP Agent

Autonomous loop AUDIT (parallel) → VALIDATE → FIX → VERIFY → CHECK with stopping criteria.

Aligned with the Anthropic 2026 pattern (official code-review plugin):

AUDIT phase in parallel (4 sub-agents: qa-security, qa-perf, wcag-audit, qa-claudemd)
VALIDATE phase filters out false positives (1 sub-agent per finding)
High-signal filter: excludes nitpicks/style
Auto-scope git diff main...HEAD by default

Context

$ARGUMENTS

Goal

Run a continuous quality improvement loop: audit the project in parallel, validate findings (false-positive filter), fix high-signal P0/P1 issues, verify tests, and repeat until the target score is reached.

Parameters (extract from $ARGUMENTS)

Target score: minimum score to stop (default: 90/100)
Max iterations: maximum number of cycles (default: 5)
Domains: security, perf, a11y, claudemd (default: all)
Severity: P0+P1 (default), or P0 only
Scope: git diff main...HEAD by default, or explicit path/glob/--full

Flags

Flag	Effect
`--audit-only`	Audit + report, no FIX (read-only mode, equivalent to the Anthropic plugin)
`--comment`	Post inline on the current PR via `gh pr comment` (requires gh + open PR)

Workflow

AUDIT (4 parallel sub-agents) → VALIDATE (false-positive filter)
  → FILTER (high-signal P0/P1 only) → FIX (unless --audit-only)
  → VERIFY (tests) → CHECK (criteria) → LOOP or STOP

AUDIT: 4 Task sub-agents in parallel (qa-security/qa-perf/wcag-audit/qa-claudemd)
VALIDATE: 1 sub-agent per finding to confirm or reject
FILTER: excludes nitpicks/style, keeps only high-signal P0/P1
FIX: fix P0 then P1 with TDD, atomic commits (skipped if --audit-only)
VERIFY: full tests, lint, type-check, + re-run qa-security on the fixed files (a fix can introduce a vuln that tests miss) — revert on regression
CHECK: score >= target AND 0 P0/P1 AND the post-fix security re-scan is clean → STOP, otherwise → AUDIT

Read the full file on GitHub · 111 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.

3d ago First seen · 111 lines · 0 tokens per session scan A afa28097cbf3

Subscribe to this mod's changes

qa-loop is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,209 tokens. 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 Code review Security agentic-ai ai-coding anthropic claude-ai cli-tool

qa-loop

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

QA-LOOP Agent

Context

Goal

Parameters (extract from $ARGUMENTS)

Flags

Workflow

What this file has done since we first saw it

Other commands, from other repositories

github

review

assemble-team

review-code

discovery

persona-panel