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/commands/vinnie357/claude-skills/new-story)<a href="https://agentmods.dev/commands/vinnie357/claude-skills/new-story"><img src="https://agentmods.dev/badge/commands/vinnie357/claude-skills/new-story/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/commands/vinnie357/claude-skills/new-story"><img src="https://agentmods.dev/badge/commands/vinnie357/claude-skills/new-story.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 | $0.00026 | $0.00899 |
| Opus 5 | $0.00013 | $0.00449 |
| Sonnet 5 | $0.00005 | $0.00180 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
new-story scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Author a new Gherkin user story compatible with the /qa validator. Runs the qa-author agent (haiku) which asks a short questionnaire and writes a parser-valid file to docs/user-stories/<persona>/<slug>.md. The resulting story can be validated end-to-end against the running application by running /qa docs/user-stories/<persona>/<slug>.md.
What it does:
- Resolve persona + slug — accept either
<persona>/<slug>shorthand or a bare<slug>paired with--persona=<name>. Validate persona against the repo's allowlist at.qa/personas.toml(fall back to a default set if absent). Validate slug against^[a-z0-9]+(-[a-z0-9]+)*$. - Confirm the file does not exist at
docs/user-stories/<persona>/<slug>.md. Slug uniqueness is scoped per-persona — the same slug under two different personas is allowed and produces two distinct files. - Spawn
qa-author— Reads the parser spec at/qa:qareferences/gherkin-format.mdand the skeleton attemplates/user-story.md, then runs the questionnaire. - Questionnaire — Asks for the feature title, primary actor, app URL, optional shared seed data, golden-path scenario name + steps, and optional edge scenarios + steps. Uses
AskUserQuestionwhen available. Persona is pre-filled; confirms only when ambiguous. - Compose + self-validate — Builds the Gherkin (including the
@persona:<name>tag and a**Persona**: <name>prose line above the fence), re-checks it against the parser rules, and only writes the file when the output is valid. - Write — Writes
docs/user-stories/<persona>/<slug>.md. Refuses to overwrite if the file already exists.
Arguments:
<persona>/<slug>(shorthand) or<slug> --persona=<name>— the persona segment selects the destination directory; the slug becomes the file name.--feature=<short-title>— optional default offer for the feature-title question.
Examples:
/qa:new-story editor/cell-regenerate
/qa:new-story cell-regenerate --persona=editor --feature="Editor regenerates a presentation cell"
/qa:new-story owner/share-workbook
/qa:new-story administrator/audit-log --feature="Admin exports the audit log"
The same slug under two personas is valid:
/qa:new-story owner/cell-create # writes docs/user-stories/owner/cell-create.md
/qa:new-story editor/cell-create # writes docs/user-stories/editor/cell-create.md
Skills the author loads (no globs — explicit names):
/qa:qa/core:anti-fabrication/core:nushell
Task instructions:
Use the qa-author subagent. Parse the argument:
- If the first positional contains exactly one
/, split intoPERSONA/SLUG. If it contains zero/, the first positional isSLUG; require--persona=<name>. Multiple/is an error. - Validate
PERSONAagainst<REPO_ROOT>/.qa/personas.toml(or the default set{owner, editor, viewer, cross-persona, administrator}if the file is absent). - Validate
SLUGagainst^[a-z0-9]+(-[a-z0-9]+)*$. - Compute the resolved target path:
<REPO_ROOT>/docs/user-stories/<PERSONA>/<SLUG>.md.
Verify the resolved target does not exist before spawning the agent — refuse to overwrite. Pass RAW_SLUG, PERSONA, the --feature value if provided, and the repo root (current working directory unless the path is in a subrepo) to the agent.
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.
- 7d ago First seen · 54 lines · 26 tokens per session scan A 3e6f47941ffb
new-story is a command published in the GitHub repository vinnie357/claude-skills (25 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 899 once invoked, about $0.0001 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 2026-09-04.
Other commands, from other repositories
playwright-test-heal
Run all my tests and fix the failing ones.
paul:verify
Guide manual user acceptance testing of recently built features.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
ui-snapshot.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.