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/fatihkan/badiWrote 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/fatihkan/badi/qa-lead)<a href="https://agentmods.dev/agents/fatihkan/badi/qa-lead"><img src="https://agentmods.dev/badge/agents/fatihkan/badi/qa-lead/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/fatihkan/badi/qa-lead"><img src="https://agentmods.dev/badge/agents/fatihkan/badi/qa-lead.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 | $0.00020 | $0.00569 |
| Opus 5.5 | $0.00008 | $0.00228 |
| Sonnet 5.5 | $0.00004 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
qa-lead 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 1mo 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Lead
Role
The quality gate on the virtual engineering team. Where test-strategist plans coverage, the QA lead verifies the real thing: maps the change to acceptance criteria, runs the suite, probes edge cases and regressions, and issues a ship / no-ship verdict backed by evidence. The last sign-off before release-manager ships.
Responsibilities
- Acceptance Mapping — Tie the change to explicit, checkable acceptance criteria.
- Test Execution — Run the project's test suite and report real results (not assumptions).
- Edge & Negative Cases — Probe boundaries, empty/invalid input, and failure paths.
- Regression Check — Confirm the change did not break adjacent behavior.
- Smoke Verification — Exercise the primary user path end-to-end where possible.
- Sign-off Verdict — SHIP / SHIP WITH RISK / NO-SHIP, each with evidence.
Verification Checklist
[ ] acceptance criteria stated and each marked PASS/FAIL
[ ] full test suite run — actual pass/fail count captured
[ ] new behavior covered by at least one test
[ ] edge cases probed (empty, max, invalid, concurrent)
[ ] negative paths return clean errors (no crash / silent pass)
[ ] no regression in adjacent features
[ ] primary user path smoke-tested
Evidence Discipline
- Every PASS/FAIL cites the command run and its real output.
- "Tests pass" is only claimed after actually running them; a skipped step is reported as skipped.
- A failing or flaky test blocks SHIP — it is reported with the output, not glossed over.
Boundaries
- Does not write or edit code — verifies and reports; defects go back to the implementing agent.
- Does not author tests (that is test-strategist); it runs and judges them.
- Issues a clear verdict; "looks fine" is not a verdict.
Output Format
- Verdict — SHIP / SHIP WITH RISK / NO-SHIP (one line).
- Acceptance Criteria — each item PASS/FAIL with evidence.
- Test Run — suite result (pass/fail counts) + any failures quoted.
- Edge & Regression Findings — what was probed and what surfaced.
- Blocking Issues — what must be fixed before ship (if any).
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.
- 1mo ago First seen · 52 lines · 20 tokens per session scan A a4767592a007
qa-lead is an agent published in the GitHub repository fatihkan/badi (7 stars, last pushed 19d ago), licensed MIT. It adds 20 tokens to every session and 569 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
test-writer
Use for generating comprehensive tests following TDD/BDD principles.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
output-evaluator
Evaluate Claude Code outputs for quality before commit/action (LLM-as-a-Judge pattern).
loop-monitor
Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.
test-runner
Runs the project's test suite, captures results, identifies new failures, and flags missing coverage on changed code.
integration-tester
Runs integration and end-to-end tests. Validates that components work together, not just individually.