re0-plan — Claude Code skill: what it does, how to install
Initializes a .re0 iteration folder and writes its starter files before re0-loop starts. Useful for structuring work and tracking quality gates in repositories using the paperthin skill suite.
npx skills add LilMGenius/paperthin --skill re0-plan -a claude-codeWhat re0-plan does
The skill sets up .re0/iteration/<version>-<workname>/ and writes its initial content immediately, avoiding empty directories at creation. It sorts work into lightweight and full cycles. A simple fix receives only a single-paragraph RETRO.local.md describing the task.
Full cycles receive DESIGN.local.md with scope and quality gates, followed by WORKFLOW.local.md and EVIDENCE.local.md. If changes touch shippable surface, gates enforce document separation: internal agent rules go to AGENTS.md, while user-facing details stay in README. Reference notes stay flat as REF-<topic>.local.md until multiple files justify a refs/ directory.
This skill is strictly non-portable: it assumes the full paperthin suite is installed and directly calls sibling skills. It has disable-model-invocation: true, which means the human must call it directly. Once files are written, it hands control to re0-loop.
What it helps with
- initialize the iteration directory inside
.re0 - record design scope and quality gates before running the build cycle
- split documentation between
AGENTS.mdandREADME - prepare starter files for
re0-loopandre0-memo
Example prompts for the agent
- Open a lightweight iteration casebook using re0-plan
- Run re0-plan to prepare a full build cycle in
.re0
How to install re0-plan
1Skills CLI (Vercel)
npx skills add LilMGenius/paperthin --skill re0-plan -a claude-code2Manually: put the files in place
~/.claude/skills/re0-plan/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/re0-plan/
1Skills CLI (Vercel)
npx skills add LilMGenius/paperthin --skill re0-plan -a codex2Manually: put the files in place
.agents/skills/re0-plan/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add LilMGenius/paperthin --skill re0-plan -a cursor2Manually: put the files in place
.cursor/skills/re0-plan/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install LilMGenius/paperthin re0-plan2Manually: put the files in place
.github/skills/re0-plan/SKILL.md1Skills CLI (Vercel)
npx skills add LilMGenius/paperthin --skill re0-plan -a gemini-cli2Platform CLI
gemini skills install https://github.com/LilMGenius/paperthin --path skills/coil/re0-planManually: put the files in place
.devin/skills/re0-plan/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add LilMGenius/paperthin --skill re0-plan -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about re0-plan
How do I install re0-plan in Claude Code?
Run npx skills add LilMGenius/paperthin --skill re0-plan -a claude-code. This installs the skill for the Claude Code agent.
What does re0-plan do?
It initializes .re0/iteration/<version>-<workname>/ and writes initial files before re0-loop executes. Depending on cycle weight, it creates either RETRO.local.md for lightweight fixes or DESIGN.local.md, WORKFLOW.local.md, and EVIDENCE.local.md for full cycles.
Can re0-plan be used without the rest of the paperthin suite?
No, it is not portable on its own. It directly references sibling skills such as re0-loop, re0-memo, and re0-release, requiring the full paperthin package to function.
Source text
SKILL.md · MIT
--- name: re0-plan description: "Open a paperthin iteration's casebook before re0-loop's first turn — seeded with real content the moment the folder exists, never an empty directory. User-invoked, paperthin-only: assumes the full skill package installed. Run when opening a new build cycle in this repo." disable-model-invocation: true --- Open `.re0/iteration/<version>-<workname>/` and write into it in the same motion, before a single line of `re0-loop`'s cycle runs. ## Goal A cycle without a written thesis, gate list, and step plan drifts to whatever framing comes first — and a folder opened with nothing in it tells a resumed session nothing at all. `re0-plan` closes both gaps at once: the folder is never empty from the moment it's created, regardless of which weight the cycle turns out to be. It assumes the full paperthin package installed and names its sibling skills directly. It pairs with `re0-release`, which retires the folder, and `re0-memo`, which extends whatever this skill seeded instead of restarting fresh. It is not a portable planning method — the shape it writes is this repo's own convention. ## Workflow 1. Classify the cycle's weight: a fix or hardening pass with no real design surface is **lightweight**; a cycle with a direction genuinely worth arguing through is **full**. 2. Create `.re0/iteration/<version>-<workname>/` and, in the same step, write its first file — the weight decides which: - **lightweight** → `RETRO.local.md`: one paragraph naming the task and why it's lightweight. `re0-memo` extends this same file at the end; it never starts a fresh one. Stop here. - **full** → `DESIGN.local.md`: thesis, scope, and quality gates — the same content `re0-loop`'s FRAME turn expects, and enough on its own to survive a session break. When the change touches shippable surface, those gates always include an AGENTS.md/README reflection gate (see Rules). Confirm the read with `readchk`, size the tier with `modelchk`; reach for `macrothink` or another judgment skill only when the direction is genuinely contestable. 3. (full only) Write `WORKFLOW.local.md`: the numbered steps this specific cycle runs through `re0-loop`'s turn order — specific to this build, not a restatement of `re0-loop`'s generic stages. 4. (full only) Write `EVIDENCE.local.md`: the gates from `DESIGN.local.md`, listed as proof surface still to fill — the bar, not results. 5. Keep reference material flat as `REF-<topic>.local.md`; promote to a `refs/` subfolder only once it multiplies past a couple of files. 6. Hand off to `re0-loop`. Do not invoke `re0-work` here — a from-scratch restart is `re0-loop`'s own mid-cycle call, surfaced by `nba` when warranted, never a setup step. ## Rules - **The folder is never empty at creation.** Every path, lightweight or full, writes real content in the same motion the folder is made, so a session break at any point still leaves something to resume from. - **Not portable, by design.** Names other paperthin skills directly and assumes the full package installed — the opposite of the self-contained default every other skill here follows. It exists only to pair with `re0-release` and `re0-memo`, not to travel alone. - **No padding.** Lightweight gets no `DESIGN`/`WORKFLOW`/`EVIDENCE`, and its `RETRO.local.md` seed stays one paragraph — a task note, not a `WORKFLOW.local.md` in disguise. A judgment skill or `re0-work` never gets forced in "just in case." - **The folder's `<version>` is provisional.** Apply the same minor/patch discriminator `re0-release` uses — kind not size: is the change, against the artifact's own prior spec, a fix (patch) or a new capability a user newly reaches for (minor)? — and keep it contingent on any unresolved fork the cycle opens. Never pre-commit a firm bump the cycle hasn't earned; a fork that could add a skill leaves the bump undecided until it resolves. - **Docs stay aligned, like `re0-release` at ship time.** When the cycle's change touches shippable surface, its quality gates always include an **AGENTS.md/README reflection gate**, assigning each reflection to its register per AGENTS.md's docs-role split: internal mechanism/rules/anatomy → **AGENTS.md** (LLM + human, injected as instructions), user-facing catalog/experience → **README** (human-only, never injected). Never dump agent-instruction mechanism into README, and never skip README for a user-facing change. This is the plan-time complement to `re0-release`'s ship-time README step. - **negatives-as-corpus** — nothing this skill or the cycle it opens produces gets deleted; a cycle that goes wrong is retired by `re0-release`, not discarded. - Every `EVIDENCE.local.md` gate traces back to a line in `DESIGN.local.md`; don't invent proof surface `DESIGN` never asked for. ## Verification Before finishing: 1. The folder has real content from the moment it exists — no empty directory, on either path. 2. Full path: `DESIGN.local.md` states a thesis, scope, and gates; `WORKFLOW.local.md`'s steps are specific to this cycle; every `EVIDENCE.local.md` gate traces to `DESIGN.local.md`. 3. Lightweight path: `RETRO.local.md` is seeded with the task and reason, one paragraph. 4. Reference material stayed flat unless it earned a `refs/` subfolder. 5. Report which path was taken and why.
© LilMGenius · MIT · LilMGenius/paperthin