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 Init

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

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

MITAuto-check passedDevelopment

Install Codd Init

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

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

GitHub CLI
$ gh skill install yohey-w/codd-dev codd-init --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-init .claude/skills/codd-init && 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-init
GitHub stars
115
Token cost
~1.1k tokens
SKILL.md length
441 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 8 steps: Preflight before running codd init → Collect the required inputs → Choose the command → …
  • A repository does not yet have a codd/ directory
  • SKILL.md covers Usage and Instructions
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Codd Init is an agent skill from yohey-w/codd-dev. Initialize CoDD in a project and establish the first scan and validation baseline. Use when a repository does not yet have a codd/ directory, when importing initial requirements, or when bootstrapping greenfield or brownfield CoDD project structure.

Its SKILL.md is about 1.1k 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

  • A repository does not yet have a codd/ directory
  • Importing initial requirements
  • Bootstrapping greenfield
  • Brownfield CoDD project structure

Example prompts

  • “/codd-init”

Workflow steps

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

  1. Preflight before running codd init
  2. Collect the required inputs
  3. Choose the command
  4. Run the selected codd init command.
  5. Confirm the generated skeleton
  6. For an existing project, handle the bootstrap carefully
  7. Next steps immediately after init — choose greenfield or brownfield
  8. Report back with

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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    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 Init loads about 1.1k tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 441 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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). 441 words, ~1,072 tokens.

Download SKILL.mdSave it as .claude/skills/codd-init/SKILL.md (or your agent's skills folder).
name
codd-init
description
Initialize CoDD in a project and establish the first scan and validation baseline. Use when a repository does not yet have a `codd/` directory, when importing initial requirements, or when bootstrapping greenfield or brownfield CoDD project structure.

CoDD Init

Initialize CoDD in the current project, then move immediately into the first scan and validation cycle so the dependency graph starts from a clean baseline.

Usage

Run this skill when a repository does not have a codd/ directory yet and you need to bootstrap CoDD with the official codd CLI entry point.

Instructions

  1. Preflight before running codd init:

    • Work from the project root where codd/ should be created.
    • If codd/ already exists, do not re-run init. Inspect the existing CoDD setup instead.
    • If the codd command is not available, install the package so the console script is on PATH before continuing.

  2. Collect the required inputs:

    • Project name: default to the current directory name unless the user provides a better product name.
    • Primary language: choose one of python, typescript, java, or go.
    • Requirements file (optional): if the user already has a requirements document (any format — .txt, .md, .doc), use --requirements to import it. CoDD adds frontmatter automatically.

  3. Choose the command:

    • With existing requirements file (recommended):
bash
codd init --project-name "<project-name>" --language <language> --requirements <path-to-requirements> --dest .
  • Without requirements (user will add them later):
bash
codd init --project-name "<project-name>" --language <language> --dest .

  1. Run the selected codd init command.

  2. Confirm the generated skeleton:

    • codd/codd.yaml
    • codd/scan/
    • codd/reports/
    • codd/.gitignore
    • .codd_version

  3. For an existing project, handle the bootstrap carefully:

    • Do not assume old design docs already have CoDD frontmatter. Inspect them before the first scan.
    • Prefer adding frontmatter to the documents you want CoDD to track before treating scan results as authoritative.
    • Legacy annotation files under codd/annotations/ are optional and backward-compatible. Create them only if the project still uses that workflow.

  4. Next steps immediately after init — choose greenfield or brownfield:

    Greenfield (have requirements, no code yet)
    1. If you used --requirements, the requirements document is already in docs/requirements/requirements.md with CoDD frontmatter. Skip to step 2. If you did NOT use --requirements, write a requirements document (plain text is fine) and import it into the existing project:
Show full SKILL.md (106 more words)Show less
bash
codd init --project-name "<project-name>" --language "<language>" \
  --requirements <path-to-requirements> --dest .
  This works even when `codd/` already exists — it only imports the file and adds frontmatter.
  Or manually create `docs/requirements/requirements.md` with frontmatter (`node_id` and `type: requirement`).
  1. Run codd generate to auto-generate wave_config and design docs:
bash
codd generate --wave 2 --path .
  1. Scan to build the dependency graph:
bash
codd scan --path .
  1. Validate the graph inputs:
bash
codd validate --path .
  1. If validation passes, continue the normal operating cycle:
bash
codd scan --path .
codd impact --path .
Brownfield (have existing code, no requirements)
  1. Extract code structure:
bash
codd extract
  1. Generate wave_config from extracted docs (plan --init auto-detects brownfield):
bash
codd plan --init
  1. Restore design docs from extracted facts (use /codd-restore skill or CLI):
bash
codd restore --wave 0 --path .   # Infer requirements from code
codd restore --wave 2 --path .   # Reconstruct system design
  1. Scan and validate:
bash
codd scan --path .
codd validate --path .
  1. Continue with the normal operating cycle:
bash
codd impact --path .
  1. Report back with:
    • Which language option was used
    • Whether init created the skeleton successfully
    • Which documents were prepared for the first scan
    • Whether codd validate --path . passed or which issues remain

© 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-init of yohey-w/codd-dev.

Open the folder on GitHubat commit 41b5f87

Compare with similar skills

Codd Init 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 Init compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codd Init this skillyohey-w/codd-dev115—~1.1kAutomated safety check: PassMIT
Vercel Composition Patternssupabase/supabase111k59 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers296k5 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 59 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.

    296k 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 23 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 23 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 23 days ago
    Auto-check passed

  • Codd Restore

    yohey-w/codd-dev

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

    115 GitHub stars~1.3k tokensUpdated 23 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 23 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 23 days ago
    Auto-check passed

Categories

Questions about Codd Init

What does Codd Init do?

Initialize CoDD in a project and establish the first scan and validation baseline. Codd Init is an agent skill from yohey-w/codd-dev. Initialize CoDD in a project and establish the first scan and validation baseline.

When should I use Codd Init?

Codd Init fits situations like: A repository does not yet have a codd/ directory; importing initial requirements; bootstrapping greenfield; brownfield CoDD project structure.

How do I install Codd Init in Claude Code?

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

How do I install Codd Init in Codex?

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

Can I use Codd Init 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-init -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-init, .gemini/skills/codd-init, .github/skills/codd-init and .opencode/skills/codd-init in your project.

What does Codd Init need to run?

SKILL.md names no scripts, command-line tools or credentials: Codd Init is instructions for the agent only.

Does Codd Init 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 Init 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 Init use?

Codd Init 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 Init use?

About 1.1k tokens (SKILL.md is roughly 4.3k 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 Init?

Skills that share tags, products or a category with Codd Init: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 296k 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 Init?

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.