/repo-harness-plan
Interactive planning entrypoint for repo-local agentic development work. Produces an approved plan before implementation, and reviews an existing plan across product, engineering, design, and DevEx dimensions.
$ npx -y skills add Ancienttwo/repo-harness --skill repo-harness-plan --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/repo-harness-plan
Context preview
The summary Claude sees to decide when to auto-load this skill.
Interactive planning entrypoint for repo-local agentic development work. Produces an approved plan before implementation, and reviews an existing plan across product, engineering, design, and DevEx dimensions.
SKILL.md
repo-harness-plan.SKILL.mdname: repo-harness-plan description: Interactive planning entrypoint for repo-local agentic development work. Produces an approved plan before implementation, and reviews an existing plan across product, engineering, design, and DevEx dimensions. when_to_use: "repo-harness-plan, plan repo-local agentic workflow work, design repo-harness change, review repo-harness plan, engineering review harness plan"
repo-harness-plan
Canonical rule owner for plan creation and plan review. Router-only: shared preflight, mode selection, and cross-mode boundaries. Mode protocol lives under `references/`.
Shared Preflight
1. Confirm the working repo with `pwd` or `git rev-parse --show-toplevel`. 2. Run `bun scripts/inspect-project-state.ts --repo <repo> --format text` when available.
Mode Selection
- No plan exists yet, or the user wants a decision-complete plan for repo-harness workflow work -> `references/create.md`.
- A plan already exists and the user wants a review before implementation -> `references/review.md`.
Boundaries
- Neither mode edits implementation files by default; review is fully read-only, and create may only capture a plan artifact through `repo-harness run capture-plan`.
- Does not run `repo-harness run plan-to-todo` from either mode; that requires explicit implementation approval handled outside this package.
File-backed workflow harness for reliable Claude Code and Codex sessions.
Repo: Ancienttwo/repo-harness
Other skills on repo-harness.
- /claude-plan
Get an independent architecture/implementation plan from Anthropic Claude (Fable, a different vendor's model) running Claude Code's native plan mode, from inside a non-Claude host such as Codex. Use mid-execution when work hits a genuine design fork or high-stakes decision that
Open skill - /repo-harness-chatgpt
Canonical rule owner for repo-harness ChatGPT integration -- Oracle-first browser/GPT Pro consult and continuation, MCP Connector setup, MCP bridge planning handoff, and Connector invocation read-back evidence.
Open skill - /repo-harness-cross-review
Independent cross-model review of the current review scope (branch diff plus staged, unstaged, untracked changes) from the opposite vendor's model. Catches spec drift, missing edge cases, and fake tests self-review cannot see. Use before merging, after a tricky change, or a
Open skill - /repo-harness-product
Canonical rule owner for PRD drafting, Sprint planning/execution, and native Goal-session preparation from repo-harness planning artifacts.
Open skill - /repo-harness-setup
Canonical rule owner for installing, migrating, upgrading, repairing, scaffolding, and capability-configuring the repo-harness workflow in a repository.
Open skill