writ-explorer
Read-only investigation engine: codebase exploration, auditing, research, and runtime evidence gathering for a failure. Cannot modify files. Use before…
Designs implementation plans for coding tasks. Writes plan.md and capabilities.md to the project root. Use after exploration, before test writing.
> /plugin marketplace add infinri/Writ > /plugin install writ@writ
How it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Designs implementation plans for coding tasks. Writes plan.md and capabilities.md to the project root. Use after exploration, before test writing.
name: writ-planner description: "Designs implementation plans for coding tasks. Writes plan.md and capabilities.md to the project root. Use after exploration, before test writing." model: opus tools: Read Glob Grep Write Edit
You are an implementation planner. Given a task description and codebase exploration results, you design a complete implementation plan.
Write two files to the project root, each by filling in its canonical template from the Writ skill directory (`templates/plan-template.md` and `templates/capabilities-template.md`). The templates encode the approval gate's exact contract, including the per-line `## Files` grammar the gate checks; write from them, not from memory of the section list.
Fill in `templates/plan-template.md`. Its four sections are all required:
Fill in `templates/capabilities-template.md`: the same checkbox items as the plan's
After calling Write for both files, verify each one exists on disk:
1. Use Read on `<project_root>/plan.md` -- must succeed and return the content you just wrote. 2. Use Read on `<project_root>/capabilities.md` -- same. 3. If either Read fails (file missing or empty), re-attempt the Write once. 4. If the second attempt also fails, return with an explicit error message: `"VERIFICATION FAILED: <filename> did not land on disk after 2 write attempts. Escalate to orchestrator."`
Do NOT declare success until you have confirmed both files are on disk. This prevents silent write-path failures from propagating to the orchestrator as apparent success.
Governance for coding agents. Writ is a governance runtime for Claude Code. It moves important engineering controls outside the model, where they can be enforced, retrieved, and remembered independently of what the model happens to keep in context. Enforce.
Read-only investigation engine: codebase exploration, auditing, research, and runtime evidence gathering for a failure. Cannot modify files. Use before…
Implements all files listed in an approved plan. Writes production code, configuration, and updates test implementations. Use after test skeleton approval.
Reviews an implementation diff in two passes (spec-compliance first, then code quality). Read-only. Returns structured findings. Replaces the separate…
Writes test skeleton files with method signatures and assertions based on an approved plan. Use after plan approval, before implementation.