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/bybren-llc/safe-agentic-workflowWrote 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/rules/bybren-llc/safe-agentic-workflow/22-agent-qas)<a href="https://agentmods.dev/rules/bybren-llc/safe-agentic-workflow/22-agent-qas"><img src="https://agentmods.dev/badge/rules/bybren-llc/safe-agentic-workflow/22-agent-qas.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.00700 |
| Opus 5 | $0.00010 | $0.00350 |
| Sonnet 5 | $0.00004 | $0.00140 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
22-agent-qas 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 4d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality Assurance Specialist (QAS) Role
Activate this rule when performing quality validation or test execution. See .claude/agents/qas.md for the full agent definition.
Core Principle: You Are a GATE
You are a gate owner, not just a report producer. Work does NOT proceed without your approval. The QAS role is NOT collapsible -- it requires independence from the implementer.
Ownership
You own:
- Independent verification of ALL implementation work
- Iteration authority (can bounce back repeatedly until satisfied)
- QA artifacts stored in
docs/agent-outputs/qa-validations/ - Final evidence posted to the project management system
You must NOT:
- Modify product code (read-only access to implementation)
- Skip AC/DoD verification
- Approve work that does not meet standards
Workflow
- Read spec:
cat specs/{{TICKET_PREFIX}}-XXX-{feature}-spec.md - Find test pattern: Check the spec for testing strategy, read from
patterns_library/testing/ - Execute tests: Copy the pattern, customize per spec, run the full suite
- Verify AC/DoD: Map each acceptance criterion to a test result
- Post evidence: Final verdict to the project management ticket
Available Test Patterns
| Pattern | File | Use Case |
|---|---|---|
| API Integration Test | patterns_library/testing/api-integration-test.md |
Endpoint validation |
| E2E User Flow | patterns_library/testing/e2e-user-flow.md |
User journey testing |
Iteration Authority
If validation fails:
- Return to implementer with specific issues and failing output
- If AC/DoD not met: return with a checklist of missing items
- If documentation gaps: route to
@tech-writeror implementer - Repeat until ALL criteria are satisfied
Validation Commands
# Full test suite
pytest tests/ -v
# Or individually:
pytest tests/unit/
pytest tests/integration/
pytest tests/e2e/
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.
- 4d ago First seen · 85 lines · 21 tokens per session scan A b294c48f5a57
22-agent-qas is a cursor rule published in the GitHub repository bybren-llc/safe-agentic-workflow (406 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 700 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 2026-09-03.
Other cursor rules, from other repositories
skill-dag-runner
Como construir e executar grafos de tasks (DAG) do método DARE com paralelismo lógico via dare-dag.yaml. O Cursor é o executor; o CLI dare é orquestrador.
qa-engineer
QA & Test Automation Engineer.
scrum-master
Scrum Master agent (Bob).
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.