agentleFS
Sign inStart free
hanzwhanzw/potato-chips/skills/codebase-intelligence/SKILL.md

codebase-intelligence

Skill1 starsChanged 3 months agoMITView on GitHub

Use the global codebase MCP for repository-scale code navigation: locating symbol declarations or implementations, tracing callers and references, impact analysis, and understanding relationships across files or modules. Trigger before broad grep or full-file reads when the task is primarily about code symbols and their relationships.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. gerivdb/SKILLS★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the MCP server named codebase as a semantic index.

    line 8
  2. Very specific:

    Start with get_symbols_overview or find_symbol.

    line 11
  3. Very specific:

    Use find_referencing_symbols, find_implementations, or declaration tools for relationships and impact.

    line 12
  4. Distinctive:

    Use host-agent tools for edits, shell commands, and exact text searches.

    line 15
  5. Distinctive:

    Verify conclusions against affected code and tests before making a claim.

    line 16
  6. Distinctive:

    Do not use Serena onboarding or memory tools.

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Codebase Intelligence

Use the MCP server named codebase as a semantic index. Keep repository files, tests, and live reads as current truth.

  1. Start with get_symbols_overview or find_symbol.
  2. Use find_referencing_symbols, find_implementations, or declaration tools for relationships and impact.
  3. Batch independent lookups in one turn; request symbol bodies only when needed.
  4. Use host-agent tools for edits, shell commands, and exact text searches.
  5. Verify conclusions against affected code and tests before making a claim.

Do not use Serena onboarding or memory tools. Do not create project memories. The global integration is intentionally read-only and ReMe remains the durable memory owner. If codebase is unavailable, fall back to native search and state that semantic lookup was unavailable.

Skip this Skill for a single known file, a literal text search, or non-code documentation where native read/search is simpler.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free