qa

A fresh-context quality checker that compares completed feature, project, or product work with its written specification.

In plain words
What is it for?
It is for validating requirements, listing pass or fail results, and reporting issues by severity without validating individual tasks.
Why use it?
It reduces the risk of accepting work because the implementer's reasoning sounded convincing. It checks the result independently and reports whether it is ready.

Agent

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.

agentmods
npx agentmods add agents/agenturehq/agenture-loop/qa
Clone the repo
git clone --depth 1 https://github.com/AgentureHQ/agenture-loop
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,282 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00069 $0.01282
Opus 5 $0.00034 $0.00641
Sonnet 5 $0.00014 $0.00256
Haiku 4.5 $0.00007 $0.00128

Measured yesterday against content hash 2d022320534b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

plugins/agn/agents/qa.md · 123 lines

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:

  • Levelfeature | 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 under docs/<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:

  1. New functionality delivered in the feature scope behaves end-to-end against the spec's acceptance criteria.
  2. Prior features or adjacent areas still work (regression check).

Process:

  1. Read the spec (feature body + linked spec).
  2. Run the project's integration/e2e tests if present.
  3. Supplement with manual checks for any acceptance criterion not covered by automated tests.
  4. Focus on interfaces between components and realistic user paths — that is where implementer reasoning is thinnest.
  5. 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.

Read the full file on GitHub · 123 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. yesterday First seen · 123 lines · 69 tokens per session scan A 2d022320534b

Subscribe to this mod's changes

qa is an agent published in the GitHub repository AgentureHQ/agenture-loop (2 stars, last pushed 2mo 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. 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.