Mmcp.market

rewrite-plan skill

by nexu-io·nexu-io/open-design·98k stars·Apache-2.0

Author a long-running multi-file rewrite plan that subsequent patch-edit + diff-review + build-test stages will execute, with explicit ownership boundaries and patch-safety guarantees.

A100/100content scan

Is the rewrite-plan skill safe?

Clean: nothing in its files matched our rules. We read 2 files in the folder on 2026-09-28.

No findings.

Install the rewrite-plan skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description. 

git clone --depth 1 https://github.com/nexu-io/open-design.git /tmp/open-design
mkdir -p ~/.claude/skills
cp -r /tmp/open-design/plugins/_official/atoms/rewrite-plan ~/.claude/skills/rewrite-plan
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

Rewrite plan

Spec §20.3 / §21.3.2: scenario 4 (design → deliverable production code) requires a contract-shaped rewrite plan before the agent starts editing files. The plan is the audit trail every subsequent stage references; without it the patch path slides into "refactor everything that looks wrong" and the build breaks in unreviewable ways.

Inputs

  • code/index.json from code-import.
  • token-map/*.json from token-map.
  • The active design system DESIGN.md (already in prompt).
  • The user's tune intent (typically a short brief).

Output

project-cwd/
└── plan/
    ├── plan.md           # human-readable narrative
    ├── ownership.json    # { file: '...', layer: 'leaf' | 'shared' | 'route' | 'shell' }
    ├── steps.json        # ordered { id, files[], rationale, risk: 'low' | 'medium' | 'high' }[]
    └── meta.json         # { generatedAt, atomDigest, tokenMapDigest }

steps.json is the input patch-edit reads one entry per iteration. ownership.json is the source of truth for "which files belong to a single component vs. shared infrastructure"; patch-edit refuses to touch a shell-tier file unless the matching step has risk: 'high' and the user explicitly confirmed.

Convergence

The atom completes when plan.md is non-empty AND steps.json contains at least one step.

Anti-patterns the prompt fragment forbids

single step. Break into per-component steps.

  • Plans that include "rewrite the whole component library" as a
  • Plans that don't classify ownership.
  • Plans that don't list a build-test step at the end.

Status

Implemented by the daemon runner in apps/daemon/src/plugins/atoms/rewrite-plan.ts. It classifies ownership and writes plan.md, steps.json, and ownership.json.

More skills from nexu-io/open-design

  • Aarticle-magazineHuashu / huashu-md-html-inspired magazine article layout for turning Markdown or notes into a polished long-form HTML essay.
  • Aaudio-jingleAudio generation skill — jingles, beds, voiceover, and sound effects. Routes music requests to Suno V5 / Udio / Lyria, speech to MiniMax TTS / FishAudio / ElevenLabs V3, and SFX to ElevenLabs SFX or AudioCraft. Output is one MP3/WAV file saved to the project folder.
  • Aaudio-jingleAudio generation skill — jingles, beds, voiceover, and sound effects. Routes music requests to Suno V5 / Udio / Lyria, speech to MiniMax TTS / FishAudio / ElevenLabs V3, and SFX to ElevenLabs SFX or AudioCraft. Output is one MP3/WAV file saved to the project folder.
  • Ablog-postA long-form article / blog post — masthead, hero image placeholder, article body with figures and pull quotes, author byline, related posts. Use when the brief asks for "blog", "article", "post", "essay", or "case study".
  • Ablog-postA long-form article / blog post — masthead, hero image placeholder, article body with figures and pull quotes, author byline, related posts. Use when the brief asks for "blog", "article", "post", "essay", or "case study".
  • Abuild-testRun the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
  • Acard-twitterTwitter quote or data card designed to pair with a post.
  • Acard-xiaohongshuXiaohongshu-style knowledge cards, arranged as a swipeable multi-card carousel.
  • Aclinical-case-reportStructured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds", "case summary", or "patient presentation".
  • Aclinical-case-reportStructured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds", "case summary", or "patient presentation".
  • Acode-importRead an existing repository's structure into the project cwd as a normalised snapshot the agent can analyse without re-walking the tree on every turn.
  • Acodex-interactive-capability-mapTurn a long-form article, thread, memo, or product narrative into a compact clickable capability map with a workflow loop, use-case matrix, and responsive detail panel.

All agent skills → · MCP servers