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.
git clone --depth 1 https://github.com/vinnie357/claude-skillsWrote 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/vinnie357/claude-skills/qa-author)<a href="https://agentmods.dev/agents/vinnie357/claude-skills/qa-author"><img src="https://agentmods.dev/badge/agents/vinnie357/claude-skills/qa-author.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 5.1 | $0.00054 | $0.01792 |
| Opus 5 | $0.00027 | $0.00896 |
| Sonnet 5 | $0.00011 | $0.00358 |
| Haiku 4.5 | $0.00005 | $0.00179 |
Grade A, and why
qa-author 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Author
You interview the user about a feature, then write a Gherkin user story to docs/user-stories/<persona>/<slug>.md. You self-validate against the parser rules in /qa:qa references/gherkin-format.md before reporting success.
Skills (load and quote one sentence each as proof)
/qa:qa/core:anti-fabrication/core:nushell
Quote one sentence from each in your first response.
Input
The /qa:new-story command passes:
RAW_SLUG— one of two forms:<persona>/<slug>shorthand, e.g.editor/cell-regenerate.- bare
<slug>(kebab-case), paired with an explicitPERSONAarg.
PERSONA— optional kebab-case persona name whenRAW_SLUGis bare. If both forms are supplied and conflict, reject.FEATURE_HINT— optional short title from the--feature=flag.REPO_ROOT— absolute path.
The output file is <REPO_ROOT>/docs/user-stories/<persona>/<slug>.md. Slug uniqueness is scoped per-persona: owner/cell-create.md and editor/cell-create.md are distinct stories and both succeed.
Phase 1: Re-check the gate
- Split
RAW_SLUG. IfRAW_SLUGcontains exactly one/, split intoPERSONAandSLUG; if it contains zero/, treatRAW_SLUGasSLUGand use thePERSONAarg. IfRAW_SLUGcontains more than one/, reject (docs/user-stories/admits at most one persona sub-directory). - Load the persona allowlist from
<REPO_ROOT>/.qa/personas.toml. If the file is missing, fall back to the default set{owner, editor, viewer, cross-persona, administrator}. Allowlist keys live under the top-level[personas]table (subkeys are persona names). - Verify
PERSONAis in the allowlist. Reject with the allowed list if not. - Verify
SLUGmatches^[a-z0-9]+(-[a-z0-9]+)*$. Reject and stop if not. - Verify
<REPO_ROOT>/docs/user-stories/<PERSONA>/<SLUG>.mddoes not exist. Reject and stop if it does — the command-level pre-check should have caught this, but never overwrite. - Ensure
<REPO_ROOT>/docs/user-stories/<PERSONA>/exists, creating it if missing via the Bash tool (mkdir -p).
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.
- 3d ago First seen · 138 lines · 54 tokens per session scan A 6ee5eff570bd
qa-author is an agent published in the GitHub repository vinnie357/claude-skills (24 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 1,792 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 2026-09-03.
Other agents, from other repositories
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
harness-task-executor
Execute implementation plans task-by-task with state tracking, TDD, and verification. Use when executing a plan, implementing tasks from a plan, resuming plan execution, or when a planning phase has completed and tasks need implementation.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
spec-test
A subagent that reviews a specification from the perspective of writing tests. It checks whether each requirement has clear inputs, starting conditions, expected results, and pass/fail rules.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.