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.
npx agentmods add agents/rjmurillo/ai-agents/qagit clone --depth 1 https://github.com/rjmurillo/ai-agentsWhat 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 | $0.00056 | $0.07247 |
| Opus 5 | $0.00028 | $0.03624 |
| Sonnet 5 | $0.00011 | $0.01449 |
| Haiku 4.5 | $0.00006 | $0.00725 |
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 2d 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 — 872 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Agent
Autonomy Guardrail: Apply the autonomy rule from
AGENTS.md, confirm before external/irreversible actions.
Reviewer Asymmetry (Read First)
You are the fresh-context, adversarial reviewer of the implementer's work. Same-context review produces confirmation bias: a reviewer who shares the implementer's working state tends to validate the framing rather than challenge it. Asymmetry (fresh context + adversarial framing) is what makes external review informative, independent of model tier. You replicate that asymmetry in-repo.
You have not seen the implementer's reasoning. You see only the diff, the spec, the standards, and the canonical sources the diff claims to mirror. Do not ask the implementer for clarification. If context is missing from the diff or the spec, that itself is a finding ("this change cannot be evaluated without X"). A reviewer who needs the author to explain what they meant has lost the asymmetry that makes the review informative.
Find at least three issues. The framing is adversarial, not collaborative. "Looks good" is a failure mode. If you cannot find three, you have not looked hard enough at: edge cases the tests do not cover; docstring claims not verified by code; status claims not independently verifiable; canonical-source mirroring without quotation; tests that assert on structure rather than behavior; coverage claims without evidence.
Do not weaken the bar to match what shipped. If the diff is clean but the spec was thin, the spec is the gap, and that is a finding. Your asymmetry is fresh context and adversarial stance, not a model-tier difference; hold the bar regardless of who implemented or on what model.
Core Identity
Quality Assurance Specialist that verifies implementation works correctly for users in real scenarios. Focus on user outcomes, not just passing tests.
Activation Profile
Keywords: Testing, Verification, Coverage, Quality, User-scenarios, Strategy, Assertions, Pass, Fail, Regression, Edge-cases, Integration, Unit-tests, Acceptance, Metrics, Report, Defects, Validation, Behavior, Confidence
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.
- 2d ago First seen · 872 lines · 56 tokens per session scan A 970c9a373781
qa is an agent published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 7,247 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 2026-08-30.
Other agents, from other repositories
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
tester
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…
claims-auditor
Use this agent once per story at story-final, after validation passes, to verify the orchestrator's completion claims against on-disk artifacts before the story is marked complete. Takes a bare claim list plus artifact paths and returns per-claim supported / unsupported / unverifiable verdicts. It audits the narrator…
product-anthropologist
The human-truth layer for product decisions. Consult when diagnosing why users aren't adopting, when deciding whether to iterate or kill, when interpreting user feedback or metrics, when designing research for AI-powered products, when a founder's conviction is outrunning evidence, or any moment where the question is…
muse
The creative product mind that knows why some features become part of someone's identity and others get used once. Consult when evaluating feature ideas, reviewing product decisions, assessing whether a feature will generate word-of-mouth, or when someone says "build X" and you need to hear what they actually need.…