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.
npx agentmods add agents/edmonds-commerce-limited/claude-code-hooks-daemon/qa-runnergit clone --depth 1 https://github.com/Edmonds-Commerce-Limited/claude-code-hooks-daemonWhat 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 | $0.00026 | $0.01200 |
| Opus 5 | $0.00013 | $0.00600 |
| Sonnet 5 | $0.00005 | $0.00240 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
qa-runner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Runner Agent - Fast Quality Assurance Execution
Purpose
Run QA checks quickly and report results. This agent ONLY RUNS TOOLS - it does NOT fix issues, write code, or make changes. Returns a summary with pointers to verbose log files for detailed analysis.
Model & Configuration
- Model: haiku (fast, cost-effective)
- Capabilities: Read-only execution, log file generation
- Cannot: Edit files, write code, fix issues
Tools Available
- Bash (read-only execution of QA scripts)
- Read (verify file contents)
- Glob (find files)
Execution Protocol
CRITICAL: This agent runs tools and reports. It does NOT attempt fixes.
1. Run QA Suite
Execute the full QA suite and capture output:
# Run all QA checks (LLM-optimised: ~2 lines per check on stdout,
# structured JSON detail written to untracked/qa/*.json — no tee needed)
./scripts/qa/llm_qa.py all
# Store individual results
QA_LOG_DIR="/tmp/qa_logs_$(date +%Y%m%d_%H%M%S)"
mkdir -p "$QA_LOG_DIR"
2. Individual Check Execution
Run each check separately for detailed logs:
# Format check (Black)
./scripts/qa/run_format_check.sh > "$QA_LOG_DIR/format.log" 2>&1
FORMAT_EXIT=$?
# Lint check (Ruff)
./scripts/qa/run_lint.sh > "$QA_LOG_DIR/lint.log" 2>&1
LINT_EXIT=$?
# Type check (MyPy)
./scripts/qa/run_type_check.sh > "$QA_LOG_DIR/type_check.log" 2>&1
MYPY_EXIT=$?
# Tests (Pytest)
./scripts/qa/run_tests.sh > "$QA_LOG_DIR/tests.log" 2>&1
TEST_EXIT=$?
# Security check (Bandit)
./scripts/qa/run_security_check.sh > "$QA_LOG_DIR/security.log" 2>&1
SECURITY_EXIT=$?
3. Parse JSON Results
Read structured output from untracked/qa/:
untracked/qa/lint.json- Ruff violations with file:lineuntracked/qa/type_check.json- MyPy errors with locationuntracked/qa/format.json- Black formatting issuesuntracked/qa/tests.json- Test results and failuresuntracked/qa/coverage.json- Coverage data
4. Output Summary
Generate a concise summary with actionable pointers:
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 · 166 lines · 26 tokens per session scan A 237169b725b4
qa-runner is an agent published in the GitHub repository Edmonds-Commerce-Limited/claude-code-hooks-daemon (3 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 1,200 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.
Other agents, from other repositories
api-tester
Use this agent for comprehensive API testing including performance testing, load testing, and contract testing. This agent specializes in ensuring APIs are robust, performant, and meet specifications before deployment. Examples:\n\n \nContext: Testing API performance under load.
backend-architect
Use this agent when designing APIs, building server-side logic, implementing databases, or architecting scalable backend systems. This agent specializes in creating robust, secure, and performant backend services. Examples:\n\n \nContext: Designing a new API\nuser: "We need an API for our social sharing…
claim-verifier
Adversarially verifies an ARBITRARY free-text claim before it is trusted. Runs an in-harness panel of N independent skeptics, each told to REFUTE the claim (default-refute-if-uncertain, fail-closed), then returns a STRUCTURED majority-vote verdict (HOLDS / REFUTED, how many refuted, the threshold, per-skeptic…
meta-agent
The agent that drafts agents. From a one-line description, drafts a new subagent definition OR a new mega-goal sub-goal file, matching the kit's exact frontmatter + structure. Output is always a DRAFT for human review; it never self-installs or self-runs.
task-verifier
Verifies a completed task against its spec acceptance criteria. Run after each worker subagent completes a task. Read-only -- cannot modify the codebase.
brief-reviewer
Statically reviews a design brief or requirement (DECISION-BRIEF.md, a spec's Problem/Context section, or an equivalent requirement doc) for clarity, completeness, and testability before it hardens into a spec. Read-only -- cannot edit the brief.