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/tomsej/pi-ext/wf-quicknpx skills add tomsej/pi-ext --skill wf-quickgit clone --depth 1 https://github.com/tomsej/pi-extWrote 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/tomsej/pi-ext/wf-quick)<a href="https://agentmods.dev/skills/tomsej/pi-ext/wf-quick"><img src="https://agentmods.dev/badge/skills/tomsej/pi-ext/wf-quick.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 | $0.00075 | $0.00735 |
| Opus 5 | $0.00037 | $0.00367 |
| Sonnet 5 | $0.00015 | $0.00147 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
wf-quick 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.
What it actually says
/wf-quick — malý task bez ceremonie
Celý cyklus v TÉHLE session — žádný soubor kontraktu, žádný worktree, žádný
wf-gate. Chat je kontrakt. Endgame: draft PR + explain. Nikdy gh pr merge.
Eskalační ventil
Překročí-li task kterýkoli limit, zastav a napiš „tohle je /wf case" —
kontrakt vytvoří skill wf z ~/Workspace/pi-ext/skills/wf/SKILL.md:
- víc než 3 akceptační kritéria,
- víc než ~5 dotčených souborů,
- migrace, destruktivní operace, auth/security, nové veřejné API.
Ventil platí i v průběhu — když task přeroste pod rukama, zastav a eskaluj, nedojížděj ho quick režimem.
Postup
- Kritéria: navrhni 1–3 pozorovatelná kritéria (styl jako ve /wf) a nech si je v chatu odsouhlasit — bez souhlasu nezačínej.
- Branch: nová branch z čisté default branche (
git switch -c <type>/<slug>). Jsi-li na feature branchi s rozdělanou prací, zeptej se. - Implementace: načti skill
tdd— jeden failing test na kritérium → minimální kód → refactor na zeleném. Test nikdy neoslabuj. - Review (risk-based): default žádné. Sahá-li změna na auth/vstupy/data
nebo o to uživatel požádá → jeden read-only reviewer přes
subagent_spawns jiným modelem nebo harnessem, než má tahle session — cross-model, jinak nemá cenu. Nálezy jsou tvrzení (severita +file:line); ověř je proti kódu, legitimní oprav sám. - Check: existující quick příkaz projektu (
npm test,make check…) — žádný nový gate skript. - Ship: commit dle skillu
commit;gh pr create --draft, titulek Conventional Commits, popis anglicky a krátce: Why / What changed / Verification (bez wf-spec markeru — quick nemá spec). - Explain: načti skill
wf-explainz~/Workspace/pi-ext/skills/wf-explain/SKILL.mdstandalone s ref range<target>...HEAD— zapíše~/Workspace/specs/<projekt>/YYYY-MM-DD-<slug>/explanation.md.
Report (česky)
Kritéria → testy, review (kdo / žádné a proč), výsledek checku, PR link, cesta k explain dokumentu.
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 · 51 lines · 75 tokens per session scan A adcd4d94e81f
wf-quick is a skill published in the GitHub repository tomsej/pi-ext (69 stars, last pushed 16d ago), licensed MIT. It adds 75 tokens to every session and 735 once invoked, about $0.0004 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
implement-slice
Implement the next smallest slice from the current plan using TDD — tests first, then code, then verification, then an atomic commit. Reads the plan from the scratchpad.
invokta-delivery
Deliver Invokta milestones and work items with TDD, adherence to versioned contracts and architecture, complete validation, and one cohesive commit per work item. Use when developing features, fixing bugs, executing roadmap milestones, or completing acceptance criteria in this repository.
ai-build
Executes one task of an already approved plan, red to green to refactor, as one logical change with a clean checkpoint that says nobody has reviewed it yet. Trigger for "implement task 3", "build this", "make the plan's next step work", "write the code for this spec". Not for deciding what to build — use /ai-spec…
gh-issue
Fetch a GitHub issue, create a branch, implement with TDD, and open a PR.
am-command-build
Implement the next task incrementally — build, test, verify, commit.
sdlc-tdd
A Single Cycle of TDD (Red-Green Phases). Reviews the provided implementation plan, and Test case, implements the next test in Red-Green, Commit cycle.