Contract Writing — Productivity skill for Claude Code
You write the contract for a task: executable tests that define "done".
How to install Contract Writing
Installs to ~/.claude/skills/jpolec-herdr-plugin-odysseus-contract-writing/SKILL.md
mkdir -p ~/.claude/skills/jpolec-herdr-plugin-odysseus-contract-writing && curl -fsSL https://raw.githubusercontent.com/jpolec/herdr-plugin-odysseus/HEAD/skills/contract-writing.md -o ~/.claude/skills/jpolec-herdr-plugin-odysseus-contract-writing/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Contract Writing does
You write the contract for a task: executable tests that define "done". Another agent will implement the task afterwards and must make your tests pass without changing them. A human approves your tests first.
Rules:
- Write tests only. Do not implement the task, not even partly, and do not change existing production code.
- Test behaviour through public interfaces (API, CLI, HTTP, exported functions), not internal details the implementer should be free to choose.
- The tests must FAIL no
Alternatives in Productivity
Full documentation available on GitHub
View Source RepositoryRelated Skills
Article Draft
Write a full article draft from an outline. Applies voice, banned-pattern rules, and section-by-section discip
Breakdown Web
Convert session plan to executable OPDRACHT.md files with 4-fase TODO workflow for Claude Code Web.
Relay Task Kernel
One handoff contract that Claude Code, Codex, Gemini CLI and Copilot all read. Zero-dependency CLI for shared
Cheap Delegate
Smart cheapest-adequate delegation — route a task to Ollama workers, OpenCode agents, Codex, Sonnet or Opus vi
M Task Planner
Dev Task Plan Workflow: Structure Implementation & Tests
Agentpack Route
Run read-only AgentPack task routing for ranked files, tests, rules, commands, and warnings.
Related Agents
Team Goal Auditor
Acceptance contract owner + goal-fidelity guard. Three enumerated phases: define (author definition-of-done.md
Sub Agent QA
PROACTIVELY used when writing test cases (Vitest/Playwright), validating code quality, or when tests fail. MUS
Acceptance Checker.Agent
Maps implementation and tests to task acceptance criteria, identifies remaining gaps, and provides a clear don