fable-discipline

fable-discipline is a Claude Code plugin that makes agentic software work follow repeatable working patterns: design before code, verify after edits, separate author from reviewer, preserve verified state between sessions, and report uncertainty honestly.

Reusable workflow discipline for Claude Code agents.

fable-disciplineis a Claude Code plugin that makes agentic software work follow repeatable working patterns: design before code, verify after edits, separate author from reviewer, preserve verified state between sessions, and report uncertainty honestly.

It is not a model upgrade and not a magic prompt pack. It shapesprocedure, not raw capability — a checklist, not a capability transplant. It can't raise a model's reasoning ceiling.

- The plugin— the generic HOW: how to plan, build, verify, review, remember, and report.
- Your repo docs— the local WHAT:CLAUDE.md,DESIGN.md,STATE.mdhold the product truth.
- Your prompt— the current goal: e.g. "Review the new onboarding flow."

/plugin marketplace add petrkindlmann/fable-discipline /plugin install fable-discipline@kindlmann-workflows

Or add the marketplace from a local path or git URL, then install.

You do not read the skills manually before every session. Install the plugin, then work normally in Claude Code. The relevant skill auto-applies based on the situation.

Plan the next billing milestone. Build the analytics dashboard redesign. Review the v1.8 changes before I merge. Resume where we left off and check the project state first. Build a CLI that scans Playwright tests for flaky selectors.

For serious product work, use the explicit milestone commands:

/milestone-research checkout-redesign /milestone-build checkout-redesign /milestone-review checkout-redesign

Use them in order. Approve the design doc between research and build.

Use this for feature work inside an existing app.

Expected behavior: Claude reads the repo'sCLAUDE.md, researches the feature, checks constraints, and writes a scoped design doc. It should not start coding yet.

Expected behavior: Claude runs an adversarial review, classifies findings honestly, and fixes them in numbered batches.

Use this for CLIs, MCP servers, plugins, libraries, SDKs, and skills packs.

Build a new CLI that scans Playwright tests and reports flaky selectors. Start with a design spec, then a checkbox implementation plan, then build it with tests.

Expected behavior: design spec first, implementation plan second, modular TDD build, review pass, live validation, release packaging.

Use this when creating a design system, writing aDESIGN.mdcontract, generating screens in Stitch/Figma, or porting generated UI to code.

Create a DESIGN.md contract for the analytics dashboard, then port the generated Stitch screen into real components. Verify the implementation against both the screen and the contract.

Expected behavior: read the full design contract, port screen-by-screen, avoid fake numbers and generic AI UI clichés, and verify against the real viewport.

Each skill is small, composable, and situation-triggered. Shared detail lives inskills/<name>/references/so the same instructions are not duplicated.

When a repo already has its own process layer

If a repo enforces its own workflow system (a GSD-style command set, the superpowers plugin, a company process plugin), the repo's layer wins — don't stack two process frameworks on the same task. fable-discipline is the portable default for repos and machines that have no such layer; in a repo that does, use only the fable-discipline skills that fill a gap the local layer doesn't cover, and follow the local layer for everything else.

- How to use this
- Copy-paste examples
- Troubleshooting— when the agent goes off the rails

# CLAUDE.md ## Verify commands - npm run lint - npm run typecheck - npm test ## Deploy model Describe what deploys on push, what requires approval, and what must not be touched casually. ## Project-specific rules List the product's moat, data honesty rules, commit style, and file locations. ## State files - .planning/STATE.md - .planning/ROADMAP.md

SeeCONTRIBUTING.mdfor the method and the ethical line. SeePROVENANCE.mdfor source attribution.

Hosted MCP server and coordination layer for AI coding agents — live API contracts, database schema, frontend/backend mismatch detection, and shared handoff tickets for Claude Code, Cursor, Codex, and Lovable.