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 skills/automagik-dev/genie/qanpx skills add automagik-dev/genie --skill qagit clone --depth 1 https://github.com/automagik-dev/genieWrote 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/skills/automagik-dev/genie/qa)<a href="https://agentmods.dev/skills/automagik-dev/genie/qa"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/qa.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.01232 |
| Opus 5 | $0.00026 | $0.00616 |
| Sonnet 5 | $0.00011 | $0.00246 |
| Haiku 4.5 | $0.00005 | $0.00123 |
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 5d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality Engineering Review
Runtime syntax: invoke the plugin copy through the active runtime's owner-qualified skill selector; use a bare selector only when intentionally selecting a user-tier copy (a separately installed personal copy; Genie no longer seeds this tier). Cross-skill prose below uses bare names as portable semantic routes; the orchestrator resolves the selector for the active runtime.
Lens
This lane treats tests as a specification and a fear-reduction device — "test until fear turns to boredom." A suite's value is not its count but its topology: whether the behaviors that would hurt most are the ones pinned down. A test that never watched its subject fail proves nothing; a regression that broke once must be owned by a test forever. Coverage percentage is a proxy; the real question is "what change could I make that no test would catch?"
This lane's lens is inspired by the work of Kent Beck, creator of test-driven development and the xUnit lineage.
Mandate
Assess and report by default. Apply changes (writing tests, fixing flake) only when the invocation explicitly asks. Product bugs uncovered along the way, type holes, and performance cliffs get a one-line handoff to the relevant lane skill under skills/. When you have enough information to act, act.
Discover the Ground Truth First
Find how this repo actually tests before judging: the framework and runner command (manifest scripts, CI workflows, CLAUDE.md/AGENTS.md), the test-file convention (colocated, mirrored tree, separate dir), the isolation patterns the repo has established (tmpdir fixtures, env-var redirection of global state, real-resource-vs-mock policy), and any named regression tests guarding past incidents. The repo's own testing doctrine — e.g. "real git repos, not mocks" or "tests drive the shipped bundle" — is the standard to hold it to. Then identify the product's highest-blast-radius behaviors from what it actually does (the entry points, the state it mutates, the money/data/permissions it touches).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 54 lines · 53 tokens per session scan A 52759ae9a7ec
qa is a skill published in the GitHub repository automagik-dev/genie (334 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 1,232 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 skills, from other repositories
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
openspec-new-change
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
gsd-audit-milestone
Audit milestone completion against original intent before archiving.
kayba-stage-7-fixer
Implement the approved fixes from the action plan and log all changes. Trigger when the user says "run stage 7", "implement fixes", "apply action plan", or when invoked by the kayba-pipeline orchestrator. Requires eval/actionplan.md to exist.