large-codebase-map

Build token-budgeted repository maps and route large-code discovery between Serena, Repomix, and Probe.

IndexedMIT

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/anders-planck-large-codebase-map

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Build token-budgeted repository maps and route large-code discovery between Serena, Repomix, and Probe. Use when a repository is unfamiliar, too large for direct reading, spans many modules, or requires a symbol and dependency overview before implementation.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/large-codebase-map

What's inside

Skill name: large-codebase-map
Description: Build token-budgeted repository maps and route large-code discovery between Serena, Repomix, and Probe. Use when a repository is unfamiliar, too large for direct reading, spans many modules, or requires a symbol and dependency overview before implementation.
License: MIT
Instructions: 19 lines in SKILL.md · view on GitHub

Files (2)

SKILL.md
openai.yaml · agents/

SKILL.md (first lines)

# Large Codebase Map

## Workflow

1. Set an explicit map token budget before collecting code.
2. Use Serena for definitions, references, and semantic relationships.
3. Use Repomix compression and token counts for a repository-wide signature map.
4. Use Probe only for high-scale AST/BM25 discovery or when the semantic backend is unavailable.
5. Rank modules by references, dependencies, task terms, and changed files.
6. Expand only the selected definitions needed for the next decision.

## Guardrails

- Do not enable Serena and Probe for the same role without explaining the fallback.
- Do not pack the entire repository when a bounded map answers the question.
- Respect ignore rules and exclude secrets, generated code, and vendored trees.
- Treat token counts as estimates unless the target model tokenizer is used.

From Anders-planck/orditra, MIT.

Signals

Stars: 0
Forks: 0
Open issues: 0
Last commit (this folder): Aug 12, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/Anders-planck/orditra
Website: github.com/Anders-planck/orditra#readme
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from Anders-planck

Cite this page

large-codebase-map skill. Agent Mart. https://agentmart.dev/skills/anders-planck-large-codebase-map (last updated 2026-10-24)