Generates a structured map of relevant files, dependencies, and test files before implementing codebase changes.
- GitHub stars
- 41,038
- Files
- 1
- Last commit
- Nov 11, 2026
- License
- MIT
- Allowed tools
- —
What does the context-map skill do?
context-map generates a structured map of relevant files, dependencies, and test files before implementing codebase changes.
Summary generated from the skill's SKILL.md.
About the context-map skill
Mapping out relevant files, dependencies, and test suites before modifying a codebase is what this skill enables. Developers use it to prevent unintended side effects by forcing an analysis phase before any code is actually written. An agent should load this tool when it receives a task description that requires changes to an existing repository, as it produces a structured markdown report instead of immediate code edits.
The process involves searching the codebase for task-related files, identifying direct imports and exports, and locating existing tests. It also scans for similar patterns in the current code to ensure consistency. The resulting context map includes tables for files to modify, dependencies that may require updates, and a list of affected test files. It concludes with a risk assessment covering public API changes, database migrations, and configuration requirements.
What an agent can do with it
- 1Pre-implementation codebase analysisAsk the agent to create a map of all files and dependencies related to a specific feature request before writing code.
- 2Identifying regression risksUse the tool to find which test files need to be updated to cover new functionality.
- 3Maintaining architectural consistencyRequest a search for existing code patterns to ensure new changes follow established styles.
- 4Assessing deployment impactEvaluate if a proposed change will require database migrations or configuration updates.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the context-map skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the context-map skill in Claude Code
~/.claude/skills/context-map/SKILL.md
$ npx degit github/awesome-copilot/skills/context-map ~/.claude/skills/context-mapInstall the context-map skill in Claude Code (project)
.claude/skills/context-map/SKILL.md
$ npx degit github/awesome-copilot/skills/context-map .claude/skills/context-mapInstall the context-map skill in Codex
~/.agents/skills/context-map/SKILL.md
$ npx degit github/awesome-copilot/skills/context-map ~/.agents/skills/context-mapInstall the context-map skill in Gemini CLI
~/.gemini/skills/context-map/SKILL.md
$ npx degit github/awesome-copilot/skills/context-map ~/.gemini/skills/context-mapInstall the context-map skill in Claude.ai
npx degit github/awesome-copilot/skills/context-map context-map && zip -r context-map.zip context-map # claude.ai → Customize → Skills → + → Create skill → Upload a skill → context-map.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work · What to fix for more points
- Source repository linked and reachablegithub/awesome-copilot/skills/context-map is public and reachablegithub.com/github/awesome-copilot/tree/HEAD/skills/context-m ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-11github.com/github/awesome-copilot/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/github/awesome-copilot/blob/HEAD/skills/context-m ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/github/awesome-copilot/blob/HEAD/skills/context-m ↗Pass
- SKILL.md follows the Agent Skills formatthe description does not say when to use the skillgithub.com/github/awesome-copilot/blob/HEAD/skills/context-m ↗Finding
SKILL.md
View on GitHubContext Map
Before implementing any changes, analyze the codebase and create a context map.
Task
{{task_description}}
Instructions
- Search the codebase for files related to this task
- Identify direct dependencies (imports/exports)
- Find related tests
- Look for similar patterns in existing code
Output Format
## Context Map
### Files to Modify
| File | Purpose | Changes Needed |
|------|---------|----------------|
| path/to/file | description | what changes |
### Dependencies (may need updates)
| File | Relationship |
|------|--------------|
| path/to/dep | imports X from modified file |
### Test Files
| Test | Coverage |
|------|----------|
| path/to/test | tests affected functionality |
### Reference Patterns
| File | Pattern |
|------|---------|
| path/to/similar | example to follow |
### Risk Assessment
- [ ] Breaking changes to public API
- [ ] Database migrations needed
- [ ] Configuration changes required
Do not proceed with implementation until this map is reviewed.
Files in this skill
1context-map skill questions
How do I install the context-map skill in Claude Code?
Run npx degit github/awesome-copilot/skills/context-map ~/.claude/skills/context-map. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the context-map skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
When should the context map be created?
The map should be generated before implementing any changes to the codebase.
Can the agent start coding immediately after generating the map?
No, the agent must wait for the map to be reviewed before proceeding with implementation.