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 skills/humanerd-drew/opencode-drewgent/qa-cyclenpx skills add humanerd-drew/opencode-drewgent --skill qa-cyclegit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWhat 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 | $0.00034 | $0.00766 |
| Opus 5 | $0.00017 | $0.00383 |
| Sonnet 5 | $0.00007 | $0.00153 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
qa-cycle 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 2d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
qa-cycle — Contract-First QA Pipeline
Purpose
Runs 3-phase QA pipeline for any task:
- CONTRACT — Define acceptance criteria before implementation
- MICRO-QA — Verify each step as it's completed
- FULL-QA — Final gate check before delivery
How It Works
Uses the QAEvidenceManager in P2-hippocampus/qa-evidence/ to:
- Create a
contract.jsonwith acceptance criteria - Record
micro-qa_*.jsonafter each step - Run
full-qa.jsonbefore delivery - Generate
.qa-evidence.jsonmanifest
Usage
skill: qa-cycle
task_id: {optional, auto-generated if omitted}
action: create_contract | record_micro | run_full_qa | status
Workflow
1. Create Contract (Before Implementation)
qa = QAEvidenceManager()
qa.create_contract(
task_id="my-task-001",
acceptance_criteria=[
{"id": "c1", "description": "Feature X works", "priority": "P0"},
{"id": "c2", "description": "Tests pass", "priority": "P0"},
]
)
2. Record Micro-QA (After Each Step)
qa.record_micro_qa(
task_id="my-task-001",
step_id="step_1",
step_description="Implemented feature X",
evidence={"files": ["feature_x.py"]},
verification={"passed": True, "score": 1.0}
)
3. Run Full-QA (Before Delivery)
result = qa.run_full_qa(
task_id="my-task-001",
criteria_verification=[...],
overall_score=0.95
)
if not result["ready_for_delivery"]:
# revision loop
Hugh Kim's Contract-First QA Principle
From the Loopy-Era Harness:
- Phase 2.5 시나리오 확정 → 구현 → micro-QA → full-QA
.qa-evidence.json증거 필수- FILESYSTEM = TRUTH: 파일에서 직접 읽어 Specialist에게 전달
Integration
- P2-hippocampus/qa-evidence/ — Evidence storage
- P4-cortex/growth/orchestrator/ — Orchestrator calls qa-cycle
- HARD hook: task_qa_gate — Blocks delivery without QA
Verification Checklist
Before marking QA complete, verify:
- All acceptance criteria have test results
- No blocker-level issues remain
- Filesystem = Truth: re-read files to confirm changes
- Evidence manifest is complete
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.
- 2d ago First seen · 102 lines · 34 tokens per session scan A f622fa022f6e
qa-cycle is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 766 once invoked, about $0.0002 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 skills, from other repositories
pm-verification-protocols
QA verification gate and evidence requirements.
wp-qa-testing
Use when WordPress software needs procedural testing framework and verification approach. Produces test strategy, test plans, test procedures, and test case specifications for developers and QA teams. Aligns to ISO/IEC/IEEE 29119-2:2021 (Test Process) with ISO/IEC TR 29119-6:2021 (Agile Tailoring). Use during…
pm-verification-protocols
QA verification gate and evidence requirements.
qa-acceptance
Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.
agent-qa-debug-fix
Debug, patch, and verify failed Agent QA runs from MCP evidence, artifacts, logs, and local code without hiding product or infrastructure defects.
agent-qa-result-triage
Triage failed Agent QA runs with MCP evidence, artifacts, logs, fixed failure categories, confidence, and actionable next steps.