A Claude Code skill that delegates implementation planning to a Fable 5.1 planning subagent, checks the plan in your main session, and, when a GitHub issue is referenced, posts the vetted plan to the issue as a comment. Then it stops.
The idea: let a dedicated planning model (Fable 5.1) produce a concrete, ordered implementation plan before any code is written, review it against the real codebase, and preserve it on the tracker. The skill never builds; you build from the plan when you choose to.
Trigger it with /fableplan, "fableplan this", or "plan this with fable", plus a task description and optionally a GitHub issue (#N, a full URL, or owner/repo#N).
The skill then runs a 5-step flow:
- Resolve the GitHub issue (only if one is referenced) so the planner works from the real requirements, not a paraphrase.
- Dispatch the Fable 5.1 Plan subagent, confirm it made no edits, and save the plan verbatim to a scratch file. The plan follows the repo's
CLAUDE.md/AGENTS.mdconventions, citesfile:linefor its claims about the code, lists open questions and assumptions, and gives acceptance criteria and exact verification commands. - Sanity-check the plan against the actual codebase (each
file:linecitation, files, symbols, conventions). It stops and asks you if the plan is structurally wrong rather than silently re-planning. - Post the vetted plan to the GitHub issue as a comment (only if one was referenced). The heading and footer name the model and effort that actually produced the plan.
- Present the plan to you, then stop. The skill never builds.
This repo is a Claude Code plugin marketplace. Inside any Claude Code session:
/plugin marketplace add richkuo/fableplan
/plugin install fableplan@fableplan
The skill is picked up automatically from the plugin's skills/ directory, and updates flow through the plugin system.
Published to npm as @fableplan/fableplan. One command copies the skill into ~/.claude/skills/:
npx @fableplan/fableplanAdd --project to install into the current repo's .claude/skills/ instead of your personal directory.
Paste this straight into a Claude Code prompt:
Install the fableplan skill from https://github.com/richkuo/fableplan into ~/.claude/skills — fetch skills/fableplan/SKILL.md and place it at ~/.claude/skills/fableplan/SKILL.md
If you use Vercel Labs' skills CLI, it discovers the skills/fableplan/SKILL.md layout automatically:
npx skills add richkuo/fableplanThis installs into .claude/skills/ (and any other agents it detects). It's a third-party tool, separate from the official plugin marketplace above.
A Claude Code skill is just a directory containing a SKILL.md, so you can also install it with one command — no clone needed:
mkdir -p ~/.claude/skills/fableplan && curl -fsSL https://raw.githubusercontent.com/richkuo/fableplan/main/skills/fableplan/SKILL.md -o ~/.claude/skills/fableplan/SKILL.mdThis puts it in your personal skills directory (~/.claude/skills/), available in every project. To scope it to a single project instead, put the file at <repo>/.claude/skills/fableplan/SKILL.md.
Start a new Claude Code session (or restart the current one), then run:
/fableplan <task to plan>
- Claude Code with access to the
fablemodel for the planning subagent. gh(GitHub CLI), authenticated, if you want the issue-comment step.- A local clone of the repository when you plan against a GitHub issue.
- The planning subagent always runs on Fable 5.1 regardless of your main session's model.
- The skill adapts to the target repo's conventions (e.g. its
CLAUDE.mdorAGENTS.md); behavior isn't hardcoded to any one project.
MIT — see LICENSE.