Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add rjmurillo/ai-agents/plugin install project-toolkitWrote 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/rjmurillo/ai-agents/qa)<a href="https://agentmods.dev/agents/rjmurillo/ai-agents/qa"><img src="https://agentmods.dev/badge/agents/rjmurillo/ai-agents/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/rjmurillo/ai-agents/qa"><img src="https://agentmods.dev/badge/agents/rjmurillo/ai-agents/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 | $0.00056 | $0.07531 |
| Opus 5.5 | $0.00022 | $0.03012 |
| Sonnet 5.5 | $0.00011 | $0.01506 |
| Haiku 4.5 | $0.00006 | $0.00753 |
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 4d 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 — 884 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.
Inspect exhaustively; do not manufacture a quota. The framing is adversarial, not collaborative. "Looks good" with no evidence of what you checked is a failure mode; so is a finding invented to hit a count. Walk the full checklist below before you score the diff: 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. When that inspection is genuinely exhaustive and surfaces nothing, say so explicitly, name what you checked, and issue a PASS verdict. A manufactured finding burns the implementer's cycle on a non-issue and teaches the next reviewer to discount yours.
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.
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.
- 4d ago Changed · +1 lines 5d6c627cc9d4
- 5d ago Changed 72d75e762ba4
- 9d ago Changed 833766c0dccc
- 15d ago Changed ec7e95395e0e
- 17d ago Changed fe0fcf9a01d9
- 20d ago Changed · +12 lines a26aec678ada
- 24d ago Changed 20cb9807b8af
- 1mo ago Changed · -1 lines 2c82c5218977
- 1mo ago Changed 203f4f4eb2fb
- 1mo ago First seen · 872 lines · 56 tokens per session scan A 486f386d3824
qa is an agent published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 7,531 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
test-judge
Evaluates test content quality including coverage, assertions, structure, and best practices.
review-feedback-applier
Classify and apply accepted review feedback from PR/MR.
verification-reviewer
Independent evidence-based check that a change is correct.
quality-gates-lens
Reviewer lens: reports the qg-verify verdict on the software-engineer's quality-gates evidence log and checks the commit policy qg-verify cannot. Read-only.
Principal software engineer
Provide principal-level software engineering guidance with focus on engineering excellence, technical leadership, and pragmatic implementation.
tdmcp-coverage-qa
Independently verifies a tdmcp coverage wave. Re-runs the coverage harness, checks that new tests assert behavior instead of only importing code, confirms thresholds were not weakened, and runs the repo gates that protect coverage work. Use after coverage writers finish.