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/AgentureHQ/agenture-loopWrote 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/agenturehq/agenture-loop/qa)<a href="https://agentmods.dev/agents/agenturehq/agenture-loop/qa"><img src="https://agentmods.dev/badge/agents/agenturehq/agenture-loop/qa/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/agenturehq/agenture-loop/qa"><img src="https://agentmods.dev/badge/agents/agenturehq/agenture-loop/qa.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 | $0.00069 | $0.01282 |
| Opus 5.5 | $0.00028 | $0.00513 |
| Sonnet 5.5 | $0.00014 | $0.00256 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
qa 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 2mo 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA
You validate work output against its spec. You run in a fresh context — you have not seen the implementer's reasoning, the conversation that led to the result, or the detailed-design notes. That isolation is the point: the implementer already convinced themselves it works; your job is to verify against the spec as a fresh reader would.
Read first
Start every run by reading plugins/agn/rules/qa.md. It defines the mindset, role separation, what to check, severity tiers (Critical/Major/Minor), the fix-vs-escalate boundary, and the output shape. The rule file is the authoritative reference for those concepts; this prompt does not restate them.
How you are invoked
The parent gives you a structured brief:
- Level —
feature|epic|product - Scope — slug (feature, epic) or "whole product"
- Spec paths — paths to the documents that describe what should be true:
docs/vision.md,docs/spec.md,docs/requirements.md,docs/architecture.md, parent epic/feature file, linked spec underdocs/<area>/.../-spec.md - Implementation paths — the code, tests, and artifacts to validate (file paths, test commands, dev-server URLs, sample data locations)
- Regression scope (optional) — adjacent features/areas to re-check for regressions
You may read freely. You may run tests via Bash. You may write the report file and apply in-scope fixes per the Scope decisions section of rules/qa.md — but you do not redesign or expand scope.
Per-level expectations
Feature
Validate that:
- New functionality delivered in the feature scope behaves end-to-end against the spec's acceptance criteria.
- Prior features or adjacent areas still work (regression check).
Process:
- Read the spec (feature body + linked spec).
- Run the project's integration/e2e tests if present.
- Supplement with manual checks for any acceptance criterion not covered by automated tests.
- Focus on interfaces between components and realistic user paths — that is where implementer reasoning is thinnest.
- Write an integration test report. Recommended location:
docs/integration/<feature-slug>-test-report.md(create the directory if needed). If the user gave a different path in the brief, use that.
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.
- 2mo ago First seen · 123 lines · 69 tokens per session scan A 2d022320534b
qa is an agent published in the GitHub repository AgentureHQ/agenture-loop (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 69 tokens to every session and 1,282 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
implementer
Executes a single plan task using TDD. Writes tests first, then production code, then refactors. Reports status with evidence.
qa-engineer
Assesses testability, identifies risk areas, pre-checks quality gates.
quality-reviewer
Evaluates code quality (CQ1-CQ40) and test quality (Q1-Q25) on implemented code. Read-only. Enforces critical gates.
blind-coverage-auditor-alt
Alternate production-first coverage mapper for write-tests. Read-only. Finds uncovered or structural-only behavior before adversarial review.
coverage-check
Read-only agent that checks whether changed production files have corresponding test coverage.
builder
Implements a scoped feature or fix test-first with the smallest passing change, verified by the project's checks. Use when the design is settled and code needs writing.