qa-agent-rules

qa-agent-rules is an agent for coding agents from Espenandreass1/agentslice. It costs 0 tokens per session (283 once invoked), scanned A, original, MIT.

Rules for an independent, release-focused quality check of software changes.

In plain words
What is it for?
Use them to test acceptance criteria, review changed files, run appropriate code checks, investigate security or data risks, and report PASS, PASS WITH NOTES, or FAIL.
Why use it?
They ensure tests and reviews are tied to the approved specification and that risks, skipped checks, evidence, and remaining notes are recorded clearly.

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/espenandreass1/agentslice/qa-agent-rules
Clone the repo
git clone --depth 1 https://github.com/Espenandreass1/agentslice

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 qa-agent-rules

README.md
[![agentmods](https://agentmods.dev/badge/agents/espenandreass1/agentslice/qa-agent-rules.svg)](https://agentmods.dev/agents/espenandreass1/agentslice/qa-agent-rules)
Your own site
<a href="https://agentmods.dev/agents/espenandreass1/agentslice/qa-agent-rules"><img src="https://agentmods.dev/badge/agents/espenandreass1/agentslice/qa-agent-rules.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 283 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 $0.00000 $0.00283
Opus 5 $0.00000 $0.00142
Sonnet 5 $0.00000 $0.00057
Haiku 4.5 $0.00000 $0.00028

Measured 3d ago against content hash 8a2fff798373, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-agent-rules 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 3d 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.

kit/docs/agents/qa-agent-rules.md · 23 lines

What it actually says

QA Agent Rules

QA is independent, critical, and release-focused.

Read

Read the active preflight, approved spec, changed files, and docs/qa/qa-plan.md. Read one earlier QA report only if directly relevant; do not bulk-read QA history.

Must do

  • Test acceptance criteria and relevant domain regressions.
  • Review changed files against the spec and ask what could break.
  • Run lint/typecheck for code changes; select build, database, full-suite, or integration checks only when the affected surface requires them. State the exact full-suite trigger, or why focused scope was sufficient.
  • Apply broader QA for shared contracts, auth/ownership, database/RLS/migrations, public user-facing flows (including commerce), build/framework configuration, or production-critical changes/releases.
  • Record chosen checks, deferred checks and why, test-execution count/purpose, evidence, blockers, non-blocking notes, confidence, and PASS, PASS WITH NOTES, or FAIL. Refresh the checkpoint's risk and telemetry fields at handoff.

Must not do

  • Repeat the whole spec or large QA tables in the report.
  • Approve unclear or untested work, ignore security/data risk, or recommend release with blockers.

Do not create parallel workers for routine testing. If no QA agent exists, switch to a critical independent QA role before returning to build or release work.

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. 3d ago First seen · 23 lines · 0 tokens per session scan A 8a2fff798373

Subscribe to this mod's changes

qa-agent-rules is an agent published in the GitHub repository Espenandreass1/agentslice (4 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 283 tokens. 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.