Codemap logo

Codemap

Organization
openyida
codemap

Generate, update, or drift-check agent-facing CodeMaps as progressive code terrain indexes for projects, features, capabilities, functions, modules, or bug chains. Use when Codex needs to inspect an unfamiliar codebase, map a feature/capability from entry to effect, create or update `mydocs/codemap/*`, answer `create_codemap`, `MAP`, `PROJECT MAP`, code terrain, impact-map, "where should the agent look first", check whether existing CodeMaps are stale after a diff, or prepare SDD-RIPER Research without loading the whole repository into context.

Overview

Publisheropenyida
Repositoryopenyida
Skill namecodemap
Stars
228
Forks
50
Bundled files
7
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 7 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by openyida on GitHub. Read the source before you install it.

Installation

Install the Codemap AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/openyida/openyida/tree/main/.agents/skills/codemap
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/openyida/openyida.git /tmp/openyida
mkdir -p .claude/skills
cp -r /tmp/openyida/.agents/skills/codemap .claude/skills/codemap
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Codemap in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Codemap on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Codemap is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Codemap

Core Position

Create CodeMaps for agents, not CodeWiki for humans.

CodeMap saves context attention, not necessarily raw token count. It does not replace source code, tests, logs, or the current Spec. It routes the agent toward the right source-linked evidence, in the right order, with progressive disclosure.

Use a CodeMap as:

  • Project CodeMap: breadth-first project terrain, capability index, module boundaries, dependency index, and drill-down pointers.
  • Feature CodeMap: depth-first capability terrain from entry to effect, including branches, dependencies, risks, and validation entry points.

Workflow

  1. Restate the requested scope and choose mode:
    • feature: capability, business feature, bug chain, API flow, function/class-centered investigation.
    • project: repository, service, package, subsystem, or first-time onboarding map.
    • drift-check: compare current diff or touched files with existing CodeMaps.
    • update-existing: refresh an existing CodeMap after code terrain changes.
  2. Before writing a durable CodeMap, tell the user why a map/update is useful, the selected mode, scope, and expected path. Do not silently write persistent maps unless current task approval already covers it.
  3. Read references/principles.md when the output shape, boundary, or CodeWiki-vs-CodeMap distinction matters.
  4. For drift checks, read references/drift-check.md.
  5. For updating an existing map, read references/update-existing.md.
  6. Inspect code with search first (rg, rg --files, language-aware tools if available). Prefer source facts over inferred naming matches.
  7. Build progressive Context Tree Nodes:
    • start with a small orientation node;
    • add capability, module, entry, branch, effect, dependency, risk, and validation nodes only where they route future context;
    • keep compact indexes as lookup tables, not as the main structure;
    • point nodes to files, functions, classes, tests, configs, logs, and related maps;
    • mark each important relationship as confirmed, inferred, or unknown.
  8. Write the map under mydocs/codemap/ when the user requests a durable artifact or the work feeds SDD-RIPER Research:
    • feature: mydocs/codemap/YYYY-MM-DD_hh-mm_<feature>功能.md
    • project: mydocs/codemap/YYYY-MM-DD_hh-mm_<project>项目总图.md
  9. Keep the CodeMap narrow enough to guide the next agent action. Do not paste large source blocks or turn it into a narrative system document.

Templates

  • For feature/capability maps, follow references/feature-template.md.
  • For project/system maps, follow references/project-template.md.
  • For drift checks, follow references/drift-check.md.
  • For existing map updates, follow references/update-existing.md.
  • If a task spans multiple repositories, create one Project CodeMap per relevant project, then add a separate interface or cross-service flow summary.

Output Rules

  • Prefer path-linked, source-grounded bullets over prose.
  • Separate Confirmed, Inferred, and Unknown.
  • Include Next Drill-Down so the next agent knows what to read only if needed.
  • Include Validation Entry so the map can feed Spec / Plan / Review.
  • Treat stale or conflicting CodeMaps as indexes to re-check, not truth.
  • Do not treat CodeMap as a changelog. Update only terrain-changing facts: entries, flows, module boundaries, dependencies, risks, validation entry points, or behavior rule locations.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Codemap AI skill do?

Generate, update, or drift-check agent-facing CodeMaps as progressive code terrain indexes for projects, features, capabilities, functions, modules, or bug chains. Use when Codex needs to inspect an unfamiliar codebase, map a feature/capability from entry to effect, create or update `mydocs/codemap/*`, answer `create_codemap`, `MAP`, `PROJECT MAP`, code terrain, impact-map, "where should the agent look first", check whether existing CodeMaps are stale after a diff, or prepare SDD-RIPER Research without loading the whole repository into context.

Why use Codemap on TypingMind?

Because you install it once and use it with any model. Codemap is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Codemap in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/openyida/openyida/tree/main/.agents/skills/codemap. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Codemap?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Codemap?

As many as you like. As long as a model supports skills, you can use Codemap with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Codemap AI skill free?

Yes. It is published on GitHub by openyida under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇