New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Codd Restore

by yohey-w in yohey-w/codd-dev

Reconstruct CoDD design documents from extracted code facts for a brownfield project.

MITAuto-check passedDevelopment

Install Codd Restore

skills CLI
$ npx skills add yohey-w/codd-dev --skill codd-restore -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install yohey-w/codd-dev codd-restore --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/yohey-w/codd-dev.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/codd-restore .claude/skills/codd-restore && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
codd-restore
GitHub stars
115
Token cost
~1.3k tokens
SKILL.md length
571 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Reconstruct CoDD design documents from extracted code facts for a brownfield project.

  • Works in 4 steps: codd/codd.yaml exists with wave_config. → codd/extracted/ contains extracted docs… → For Wave 2+, verify that earlier waves… → …
  • Needs to infer requirements
  • SKILL.md covers When to Use, Brownfield Flow, Requirements Inference (Wave 0) and Prerequisite Checks, plus 5 more sections
  • Calls python

What it does

Codd Restore is an agent skill from yohey-w/codd-dev. Reconstruct CoDD design documents from extracted code facts for a brownfield project. Use after codd extract and wave planning when the user needs to infer requirements or restore system and detailed design from existing source code rather than greenfield requirements.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development. The repository describes itself as: CoDD: Coherence-Driven Development — Claude Code plugin for cross-artifact change impact analysis. The licence is MIT.

When your agent uses it

  • Needs to infer requirements
  • Restore system and detailed design from existing source code rather than greenfield requirements

Example prompts

  • “/codd-restore”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. codd/codd.yaml exists with wave_config.
  2. codd/extracted/ contains extracted docs (run codd extract first if missing).
  3. For Wave 2+, verify that earlier waves have been restored or exist already.
  4. Confirm you are in the intended project root.

What it can do on your machine

Read from SKILL.md and the folder at commit 41b5f87. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Codd Restore loads about 1.3k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 571 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from yohey-w/codd-dev at commit 41b5f87, republished under its MIT licence (© yohey-w). 571 words, ~1,298 tokens.

Download SKILL.mdSave it as .claude/skills/codd-restore/SKILL.md (or your agent's skills folder).
name
codd-restore
description
Reconstruct CoDD design documents from extracted code facts for a brownfield project. Use after `codd extract` and wave planning when the user needs to infer requirements or restore system and detailed design from existing source code rather than greenfield requirements.

CoDD Restore

Reconstruct design documents from extracted code facts for brownfield projects. Unlike /codd-generate (which creates docs from requirements), /codd-restore asks "what IS the current design?" — reconstructing intent from code structure.

When to Use

  • After codd extract has generated extracted docs in codd/extracted/
  • After codd plan --init has generated wave_config from extracted docs (or requirements)
  • When you have an existing codebase with no design documentation
  • When you want to infer requirements from code (wave 0 / requirements docs)

Do NOT use this for greenfield projects with requirements — use /codd-generate instead.

Brownfield Flow

codd extract          # Step 1: Static analysis → codd/extracted/
codd plan --init      # Step 2: Extracted docs → wave_config (auto-detects brownfield)
codd restore --wave 0 # Step 3a: Infer requirements from code facts
codd restore --wave 2 # Step 3b: Reconstruct system design
codd restore --wave 3 # Step 3c: Reconstruct detailed design
codd scan --path .    # Step 4: Build dependency graph

Requirements Inference (Wave 0)

When restoring a document under docs/requirements/, the restore command switches to requirements inference mode:

  • Infers functional requirements from modules, classes, API routes, and function signatures
  • Infers non-functional requirements from code patterns (async = performance, rate limiting = scalability, RLS = security)
  • Infers constraints from frameworks, libraries, and architectural patterns
  • Marks non-obvious inferences with [inferred] so humans can verify

Important limitations (the prompt explicitly warns the AI about these):

  • Cannot know features that were planned but never implemented
  • Cannot distinguish bugs from intentional behavior
  • Cannot know business context not reflected in code

These are inferred requirements — describing what was built, not original intent. Human review is essential.

Prerequisite Checks

Before every restore run, verify:

  1. codd/codd.yaml exists with wave_config.
  2. codd/extracted/ contains extracted docs (run codd extract first if missing).
  3. For Wave 2+, verify that earlier waves have been restored or exist already.
  4. Confirm you are in the intended project root.

If any prerequisite fails, stop and resolve it.

Follow this loop for each wave:

  1. Restore the target wave:

    bash
    codd restore --wave 0 --path .

    Replace 0 with the current wave number.

  2. Read every restored document and confirm:

    • the content accurately describes the existing codebase
    • inferred requirements are reasonable and marked with [inferred]
    • no hallucinated capabilities were introduced
    • the document body starts directly with content, not AI meta commentary

  3. Validate frontmatter and dependency references:

    bash
    codd validate --path .

  4. Refresh the dependency graph:

    bash
    codd scan --path .

  5. Pause for HITL confirmation before the next wave:

    • After requirements inference: 推定要件を確認しました。Wave 2（システム設計の復元）に進みますか？
    • After any later wave: Wave Nの設計書を復元しました。Wave N+1 に進みますか？
Show full SKILL.md (228 more words)Show less

HITL Gates

Human review is mandatory between waves. Restored documents describe "what IS" but may misinterpret intent. Do not proceed automatically.

  • Review goal 1: confirm restored content matches the actual codebase behavior
  • Review goal 2: flag any inferred requirements that are actually bugs or unintended behavior
  • Review goal 3: add business context the AI could not infer from code

If the human rejects a wave, revise with --force, re-validate, and request approval again.

Greenfield vs Brownfield Decision

SituationCommand
Have requirements, no code/codd-generate
Have code, no requirements/codd-restore
Have both/codd-generate (requirements take precedence)
Want to infer requirements from codecodd restore --wave 0 (requirements inference)

Troubleshooting

  • Error: no extracted documents found
    • Run codd extract first to generate extracted docs from source code.
  • Error: wave_config has no entries for wave N
    • Run codd plan --init to generate wave_config from extracted docs.
  • Restored content hallucinated capabilities not in the code
    • Use --force to regenerate, or manually edit the restored document.
  • Inferred requirements too vague
    • Check that codd extract captured enough detail. Re-run extract with more source dirs if needed.

Guardrails

  • Use the codd command, not python -m codd.cli.
  • Restore one wave at a time.
  • Do not skip human approval gates — restored docs need human verification of intent.
  • Do not advance to the next wave while validation is failing.
  • Do not use restore for greenfield projects with existing requirements.

© yohey-w, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/codd-restore of yohey-w/codd-dev.

Open the folder on GitHubat commit 41b5f87

Compare with similar skills

Codd Restore next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Codd Restore compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codd Restore this skillyohey-w/codd-dev115—~1.3kAutomated safety check: PassMIT
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Vercel Composition Patterns

    supabase/supabase

    Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 58 repos~726 tokens
    DevelopmentAuto-check passed

  • Finishing a Development Branch

    obra/superpowers

    Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from yohey-w/codd-dev

All 11 skills in this repo

  • Codd Generate

    yohey-w/codd-dev

    Generate CoDD design documents for a greenfield project one wave at a time.

    115 GitHub stars~1.5k tokensUpdated 25 days ago
    Auto-check passed

  • Codd Greenfield

    yohey-w/codd-dev

    Run the CoDD greenfield autopilot: a requirements document in, a working system out, unattended.

    115 GitHub stars~2.2k tokensUpdated 25 days ago
    Auto-check passed

  • Codd Init

    yohey-w/codd-dev

    Initialize CoDD in a project and establish the first scan and validation baseline.

    115 GitHub stars~1.1k tokensUpdated 25 days ago
    Auto-check passed

  • Codd Propagate

    yohey-w/codd-dev

    Reverse-propagate source code changes back to affected CoDD design documents.

    115 GitHub stars~1.4k tokensUpdated 25 days ago
    Auto-check passed

  • Codd Impact

    yohey-w/codd-dev

    Analyze the downstream impact of changed requirements, design docs, code, or tests in a CoDD project.

    115 GitHub stars~1.5k tokensUpdated 25 days ago
    Auto-check: warnings

  • Codd Scan

    yohey-w/codd-dev

    Refresh a CoDD project's dependency graph from document frontmatter and source code.

    115 GitHub stars~1.4k tokensUpdated 25 days ago
    Auto-check passed

Categories

Questions about Codd Restore

What does Codd Restore do?

Reconstruct CoDD design documents from extracted code facts for a brownfield project. Codd Restore is an agent skill from yohey-w/codd-dev. Reconstruct CoDD design documents from extracted code facts for a brownfield project.

When should I use Codd Restore?

Codd Restore fits situations like: needs to infer requirements; restore system and detailed design from existing source code rather than greenfield requirements.

How do I install Codd Restore in Claude Code?

Run `npx skills add yohey-w/codd-dev --skill codd-restore -a claude-code`. Or copy the skill folder (skills/codd-restore in yohey-w/codd-dev) into .claude/skills/codd-restore in your project. Claude Code loads it when a task matches its description.

How do I install Codd Restore in Codex?

Run `npx skills add yohey-w/codd-dev --skill codd-restore -a codex`. Or copy the skill folder (skills/codd-restore in yohey-w/codd-dev) into .agents/skills/codd-restore in your project. Codex loads it when a task matches its description.

Can I use Codd Restore in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yohey-w/codd-dev --skill codd-restore -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codd-restore, .gemini/skills/codd-restore, .github/skills/codd-restore and .opencode/skills/codd-restore in your project.

What does Codd Restore need to run?

Going by SKILL.md and its folder, Codd Restore needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Codd Restore access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Codd Restore safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Codd Restore use?

Codd Restore is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Codd Restore use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Codd Restore?

Skills that share tags, products or a category with Codd Restore: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codd Restore?

yohey-w (a GitHub user) maintains it in yohey-w/codd-dev, which has 115 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 14, 2026.

Source: yohey-w/codd-dev on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.