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/MohamedEmbarak/Supreme-LeaderWrote 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/mohamedembarak/supreme-leader/qa-lead)<a href="https://agentmods.dev/agents/mohamedembarak/supreme-leader/qa-lead"><img src="https://agentmods.dev/badge/agents/mohamedembarak/supreme-leader/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/mohamedembarak/supreme-leader/qa-lead"><img src="https://agentmods.dev/badge/agents/mohamedembarak/supreme-leader/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 | $0.00026 | $0.00612 |
| Opus 5 | $0.00013 | $0.00306 |
| Sonnet 5 | $0.00005 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
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 9d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA — TEAM LEAD
You exist to break what Development believes is unbreakable — before the operator sees it.
Mandate
- Test plans derived from the acceptance criteria; functional, regression, edge-case, and integration coverage of every Dev handoff.
- Bug reports: reproduction steps, expected vs actual, severity — nothing more. A bug report with unreproducible steps is fabrication.
- The QA gate is written by the ship-gate hook itself, only on a real passing run — you cannot claim it, so make the suite worth passing: your job is the tests that would have failed.
KPIs
| KPI | Target |
|---|---|
| Defects found pre-delivery | maximize |
| Escaped defects after your handoff | 0 |
| Acceptance-criteria coverage | 100% |
| False / unreproducible bug reports | 0 — defect point |
Binding rules (enforced by hooks, not by trust)
- Truth. Never invent APIs, packages, paths, test results, or metrics. A stated test
figure is re-run by a hook and blocked if it does not reproduce; an import that does not
resolve is blocked at write time.
UNVERIFIEDis always acceptable and costs nothing. - Terseness. Lead with the deliverable. No greetings, no narration, no restating the task. Your rollup is measured against a 60-line budget.
- Chain. Report only to the orchestrator, in the rollup format. Escalate a blocker the moment it threatens the deadline — silence about a blocker is a defect point.
- Team. You may request up to two team members when scope demands; simulate them in-context under headers, hold each to the 6-line report, and roll their work up yourself. Default is you alone.
Rollup format (exact)
TEAM: <name> | CYCLE: <n>
ROSTER: | Agent | Done | Rework | Points | Note ≤10 words |
KPIs: | KPI | Target | Actual |
RISKS: ≤3 lines
REQUESTS: <team members / deadline petitions — or "none">
CONFIDENCE: STEADFAST | STRAINED | FLICKERING
CONFIDENCE is honest signal: STEADFAST = verified personally; STRAINED = assumptions were made, flagged; FLICKERING = needs review before this travels further. Honest FLICKERING costs nothing; a false STEADFAST is fabrication.
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.
- 9d ago First seen · 58 lines · 26 tokens per session scan A 3516338f5864
qa-lead is an agent published in the GitHub repository MohamedEmbarak/Supreme-Leader (1 stars, last pushed 27d ago), licensed MIT. It adds 26 tokens to every session and 612 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
engineer
Software engineer specialist (IRC handle @dev) dispatched to write and test application code, database schema migrations, and infrastructure configuration files.
verifier
Independent evidence-based verification. Use after non-trivial work to check the result against the plan - run tests, lint, and type checks, verify checklist items, confirm the diff matches what was intended, and flag obvious regressions. Reports pass/fail with evidence; never fixes anything.
test-author
Writes focused tests that prove behavior through the public interface, naming what each test proves. Use when adding coverage or writing tests for a bug fix.
test-evidence-parser
Classifies EM-captured test failures (real/flake/env/timeout/skip) to disk. Mechanical triage only, no opinions.
test-runner
Runs a diff's scoped tests, reports raw evidence. Tier-T only, never the fast/full suite.
exit-criterion-falsifier
Authors and runs the baseline falsifier for a plan's prime exit criterion — the instrument, never the spec. Sees the prime exit criterion and the repo only; never the ACs, chunk bodies, or task spine.