22-agent-qas

22-agent-qas is a cursor rule for Cursor from bybren-llc/safe-agentic-workflow. It costs 21 tokens per session (700 once invoked), scanned A, original, MIT.

A quality-assurance role that independently verifies whether implemented work meets its acceptance criteria. It runs the required tests, records evidence, and can reject work until the criteria are satisfied.

In plain words
What is it for?
Use it to review completed features, execute test suites, check acceptance criteria or Definition of Done, store QA evidence, and post the final verdict to the project ticket.
Why use it?
It separates testing from implementation so unfinished or incorrect work is not approved by the same person who built it. It also connects each requirement to a test result and a final decision.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: reads .claude/ paths.

Good fit Use it to review completed features, execute test suites, check acceptance criteria or Definition of Done, store QA evidence, and post the final verdict to the project ticket.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/bybren-llc/safe-agentic-workflow/22-agent-qas
Install

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.

Clone the repo
git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflow

Made for: Cursor.

Wrote 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.

agentmods badge for 22-agent-qas

README.md
[![agentmods](https://agentmods.dev/badge/rules/bybren-llc/safe-agentic-workflow/22-agent-qas.svg)](https://agentmods.dev/rules/bybren-llc/safe-agentic-workflow/22-agent-qas)
Your own site
<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>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 700 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash b294c48f5a57, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

.cursor/rules/22-agent-qas.mdc · 85 lines

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

  1. Read spec: cat specs/{{TICKET_PREFIX}}-XXX-{feature}-spec.md
  2. Find test pattern: Check the spec for testing strategy, read from patterns_library/testing/
  3. Execute tests: Copy the pattern, customize per spec, run the full suite
  4. Verify AC/DoD: Map each acceptance criterion to a test result
  5. 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:

  1. Return to implementer with specific issues and failing output
  2. If AC/DoD not met: return with a checklist of missing items
  3. If documentation gaps: route to @tech-writer or implementer
  4. 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/

Read the full file on GitHub · 85 lines

Changes

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.

  1. 4d ago First seen · 85 lines · 21 tokens per session scan A b294c48f5a57

Subscribe to this mod's changes

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.