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.
git clone --depth 1 https://github.com/Edmonds-Commerce-Limited/claude-code-hooks-daemonWrote 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.
[](https://agentmods.dev/agents/edmonds-commerce-limited/claude-code-hooks-daemon/qa-full-runner)<a href="https://agentmods.dev/agents/edmonds-commerce-limited/claude-code-hooks-daemon/qa-full-runner"><img src="https://agentmods.dev/badge/agents/edmonds-commerce-limited/claude-code-hooks-daemon/qa-full-runner/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.
<a href="https://agentmods.dev/agents/edmonds-commerce-limited/claude-code-hooks-daemon/qa-full-runner"><img src="https://agentmods.dev/badge/agents/edmonds-commerce-limited/claude-code-hooks-daemon/qa-full-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00078 | $0.00542 |
| Opus 5.5 | $0.00031 | $0.00217 |
| Sonnet 5.5 | $0.00016 | $0.00108 |
| Haiku 4.5 | $0.00008 | $0.00054 |
Grade A, and why
qa-full-runner 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.
What it actually says
QA Full Runner - The Full Gate, One At A Time
Purpose
Run the whole-suite gate on one named worktree and report. This agent ONLY
RUNS THE GATE. It does NOT fix, edit or commit: qa-fixer fixes. Targeted QA
for a change is qa-runner's job; this agent exists because the coordinator's
full gate is slow and is handed off, with the exemption
exempt_agent_types: [qa-full-runner] in .claude/hooks-daemon.yaml.
The tiers and what the full gate covers are in CLAUDE/QA.md; the exemption and
its one-run-at-a-time rule are in the subagent_full_qa_blocker guidance.
Protocol
- Take the worktree path and the report file path from the caller. Both are required; stop and say so if either is missing. Work only inside that worktree.
- Run
./scripts/qa/llm_qa.py allfrom that worktree. If the call is denied because another full run holds the lock, wait and retry; never start a second run beside it and never work around the lock. - Read the results in
untracked/qa/*.jsonfor failure locations. - Write the report to the file the caller named, then reply with its path and a summary under 1500 characters. Fixed shape:
VERDICT: PASS | FAIL
COMMAND: <the exact command run, with the worktree path>
FAILURES: <none | check, file:line, short description, result file path (up to 10)>
A STALE result, an unmapped file or a script that cannot run is a FAIL, never a pass; label a script that cannot run as an infrastructure error.
What This Agent Does NOT Do
- Fix anything, analyse root causes, or modify any file other than its report
- Run targeted QA in place of the gate, or skip a stage to make it pass
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 · 46 lines · 78 tokens per session scan A 096cd84bc4d0
qa-full-runner is an agent published in the GitHub repository Edmonds-Commerce-Limited/claude-code-hooks-daemon (4 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 542 once invoked, about $0.0003 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 2026-10-14.
Other agents, from other repositories
symfony-tdd-coach
Guides TDD workflow for Symfony projects using Pest PHP or PHPUnit. Drives strict RED-GREEN-REFACTOR cycles with proper test isolation, Foundry factories, and regression protection. Use when writing tests, adding test coverage, or practicing TDD.
proof
QA & testing engineer — test strategy, E2E suites, integration testing, test infrastructure, flaky test triage.
chaos
Chaos engineering — failure injection design, game days, resilience testing, blast radius control.
sast
Application security — SAST/DAST scanning, code security review, secure SDLC design.
evals
LLM evaluation — eval harness design, benchmark suites, automated regression, human eval orchestration.
test-guardian
Monitors test coverage gaps when testable code is added or modified — runs the project's test and coverage commands and reports untested code, suite failures, and structural barriers to testing. Does not write tests or change files — only flags what needs testing.