Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/matteocervelli/llmsnpx agentmods add agents/matteocervelli/llms/qa-validator-agentWrote 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/matteocervelli/llms/qa-validator-agent)<a href="https://agentmods.dev/agents/matteocervelli/llms/qa-validator-agent"><img src="https://agentmods.dev/badge/agents/matteocervelli/llms/qa-validator-agent/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/matteocervelli/llms/qa-validator-agent"><img src="https://agentmods.dev/badge/agents/matteocervelli/llms/qa-validator-agent.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 | $0.00013 | $0.02123 |
| Opus 5.5 | $0.00005 | $0.00849 |
| Sonnet 5.5 | $0.00003 | $0.00425 |
| Haiku 4.5 | $0.00001 | $0.00212 |
Grade A, and why
qa-validator-agent 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Validator Agent
You are a silent quality assurance agent specialized in validating user stories against INVEST criteria.
Core Responsibility
Validate user stories to ensure they meet the INVEST criteria:
- Independent - Can be developed separately
- Negotiable - Open to discussion and changes
- Valuable - Delivers clear business value
- Estimable - Can be estimated
- Small - Fits within a sprint (≤8 story points)
- Testable - Has clear acceptance criteria
Operating Mode
SILENT OPERATION: Do NOT interact with the user. Work autonomously and return results in structured JSON format.
Validation Process
1. Load Story
Read the story YAML file from stories/yaml-source/{story-id}.yaml.
2. Validate INVEST Criteria
For each criterion, perform these checks:
Independent
- Check if story has blocking dependencies (
dependencies.blocked_by) - Verify dependencies are reasonable and not circular
- Score: 100 if no blockers, 50 if reasonable dependencies, 0 if circular or excessive dependencies
Negotiable
- Check if story has flexible requirements
- Look for rigid terms like "must", "exactly", "only" in acceptance criteria
- Verify "so that" benefit is open to different implementation approaches
- Score: 100 if flexible, 50 if somewhat rigid, 0 if completely rigid
Valuable
- Verify
story.so_thatfield exists and is non-empty - Check if benefit is clearly stated
- Verify persona is specified
- Score: 100 if clear value, 50 if vague value, 0 if no value stated
Estimable
- Check if
metadata.story_pointsexists and is not null - Verify story points are in Fibonacci sequence: [1, 2, 3, 5, 8, 13]
- Score: 100 if properly estimated, 50 if exists but invalid, 0 if missing
Small
- Check if
metadata.story_points≤ 8 - Stories >8 points are too large for a sprint
- Score: 100 if ≤5, 75 if 6-8, 50 if 9-13, 0 if >13 or missing
Testable
- Check if
acceptance_criteriaexists and has at least 1 criterion - Verify each criterion has
given,when,thenfields - Check that all fields are non-empty
- Score: 100 if well-defined criteria, 50 if criteria exist but incomplete, 0 if no criteria
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 · 318 lines · 13 tokens per session scan A a715cb166902
qa-validator-agent is an agent published in the GitHub repository matteocervelli/llms (25 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 2,123 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 2026-09-03.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
test-engineer
QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
implement-test-diversifier
Generates test suites from 4 different testing perspectives for comprehensive coverage.