A workflow-contract writer turns the current discussion into one Markdown contract outside the code repository, with Czech notes and machine-readable metadata. It checks the contract with a validation command and never writes implementation code.

Use it with `/wf` when you want to capture a problem, its current behavior, a plain-language business summary, and observable acceptance criteria for later execution.

It prevents important requirements from staying scattered across chat or being guessed during coding. The separate file also keeps planning material out of commits and pull requests.

wf — Skill for Claude Code and Codex by tomsej: A workflow-contract writer turns the current discussion into one…

Install

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.

agentmods

npx agentmods add skills/tomsej/pi-ext/wf

Any agent

npx skills add tomsej/pi-ext --skill wf

Clone the repo

git clone --depth 1 https://github.com/tomsej/pi-ext

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tomsej/pi-ext/wf.svg)](https://agentmods.dev/skills/tomsej/pi-ext/wf)

Your own site

<a href="https://agentmods.dev/skills/tomsej/pi-ext/wf"><img src="https://agentmods.dev/badge/skills/tomsej/pi-ext/wf.svg" alt="Measured on agentmods" height="20"></a>

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,205 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00087	$0.02205
Opus 5	$0.00044	$0.01103
Sonnet 5	$0.00017	$0.00441
Haiku 4.5	$0.00009	$0.00220

Measured 4d ago against content hash 1a935930b7f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wf 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.

skills/wf/SKILL.md · 138 lines

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.

/wf — tvorba kontraktu

Z diskuse uděláš kontrakt. Výstup je JEDEN soubor — žádný kód, žádný git. Spuštění řeší později wf-run.

GATE = node ~/Workspace/pi-ext/wf/wf-gate.mjs Cesta: ~/Workspace/specs/<projekt>/<název>/contract.md — <projekt> = basename origin remote bez .git (fallback: adresář repa), <název> = kebab-case. Vlastní adresář — přibudou artefakty (explanation.md), archivace = jeden přesun. Mimo repo záměrně — nesmí se objevit v commitu ani PR diffu.

1. Tělo (česky, odrážky)

Co jde zjistit z repa, zjisti z repa; na zbytek se doptej — nehádej.

Styl

Používej jeden název pro jednu věc.
Piš aktivně a používej krátká běžná slova.
Jedna věta nebo odrážka obsahuje jednu hlavní myšlenku.
Vynech výplňové úvodní fráze, opakování a marketingová přídavná jména.
Stručnost nesmí odstranit podmínku, hranici ani pozorovatelné chování.

Sekce

Současné chování / reprodukce: jak to funguje teď; u bugu přesná reprodukce.
Business shrnutí: 2–4 věty pro netechnického čtenáře — v PR z toho bude anglická sekce „Why".
Akceptační kritéria: pozorovatelná chování, každé = jeden budoucí test.
- Kritérium = největší chování ověřitelné jedním testem; sdílená fixture + jiná data = JEDNO kritérium s tabulkou případů.
- Rozpočet ~12; přes 15 = slučuješ špatně, vrať se k tabulkám. Jemnější rozpad stojí jeden TDD cyklus navíc za kus.
- Pořadí kroků, remíza, hraniční případ: rozhodnutí napiš přímo do kritéria, nebo jako otevřenou otázku — nedopsané pravidlo si každý vyloží jinak a review to neodhalí.
Strategie testování: ke každému kritériu typ testu (unit/integrační/e2e), veřejné rozhraní a data. Netestovatelné kritérium nahlas teď, ne po implementaci.
Technický handoff (netriviální změny): invarianty, změněná veřejná rozhraní, současný → navržený call stack, rizika. Neznámé nevymýšlej. Invarianty pozorovatelně („stejný vstup dá stejný výstup"), nikdy jako mechanismus („stav je immutable") — implementaci volí implementátor.
Přístup: preferovaná řešení a co je vyloučené (např. „žádná nová závislost").
Non-goals: co vědomě neřešíme.
Scope: povolené soubory/moduly — wf-run z nich detekuje kolize kontraktů.
UAT: co má uživatel ověřit ručně, ze svého pohledu.

Read the full file on GitHub · 138 lines

Changes

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 First seen · 138 lines · 87 tokens per session scan A 1a935930b7f1

Subscribe to this mod's changes

wf is a skill published in the GitHub repository tomsej/pi-ext (69 stars, last pushed 17d ago), licensed MIT. It adds 87 tokens to every session and 2,205 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.

Planning Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens