- Home
- Skills
- Prompt & Skill Engineering
- codebase-map
Codebase Map 1
Turn an unfamiliar repository into compact agent context and a visual architecture map.
Free
Works with the AI Agents you already use
codebase-map
Example session with this skill installed
$codebase-map How does a new user registration flow work in this repository?
- Read your context and instructions
- Compiled the codebase-map
I have scanned the repository and indexed the registration logic. I've identified the entry points in the API gateway and traced the flow through the auth service to the persistence layer.
User Registration Flow Map
sequenceDiagram
participant U as User
participant G as Gateway (routes/auth.ts)
participant S as AuthService (services/identity.js)
participant D as Database (models/user.model.ts)
U->>G: POST /api/v1/register
G->>S: validatePayload(data)
Note over S: confirmed: uses bcrypt for hashing
S->>D: findUnique({ email })
D-->>S: null
S->>D: create({ data })
D-->>S: UserObject
S-->>G: Token + Profile
G-->>U: 201 Created
The flow is centered on routes/auth.ts and services/identity.js. The indexing identified that while the API structure is confirmed, the exact retry logic for the database connection is currently
inferred based on generic middleware patterns.
Generated Artifacts:
reports/codebase-map/core-api/index.json(Source of truth)reports/codebase-map/core-api/architecture.html(Interactive map)reports/codebase-map/core-api/context.md(Agent orientation)
Next steps
- Open
reports/codebase-map/core-api/architecture.htmlto see the full component map. - Review
evidence.mdto see the specific symbol paths forvalidatePayload. - Run a focused map on the
email-workerif you need to see the post-registration welcome flow.
Connects securely to your tools. The creator never sees your data.
About this skill
codebase-map is an agent skill that turns an unfamiliar repository into (1) a compact index an agent can retrieve from before reading source files, and (2) a visual answer to broad architecture questions or specific questions about how the repo works. Every concept, label, edge and flow is derived from repository evidence. Outputs a self-contained HTML architecture report plus context.md, evidence.md and index.json. Includes a verifier script and a tiny example app. Open source on GitHub: https://github.com/adianvel/codebase-map
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Prompt & Skill Engineering.
Requires local filesystem access. Performance on massive repos depends on clear boundaries. Visuals are limited to code evidence.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed today
- Free with an Agensi account