agentleFS
Sign inStart free
alilfrancesalilfrances/midas/skills/explore/SKILL.md

explore

Skill0 starsChanged 4 months agoMITView on GitHub

Token-cheap codebase search strategy. Use before editing unfamiliar code, when locating symbols/usages/config, or after Midas edit gate fires.

67 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use agent-context-isolation, agentica-infrastructure and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 58 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before changing symbol: grep ALL usages, not just definition.

    line 18
  2. Distinctive:

    Never read a whole file to "get context" when search can locate.

    line 20

“Common” is measured: kept by at least 6 in 10 of the 58 edited versions of this file we could read. “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

Explore

Funnel, cheapest first:

  1. Repo-context MCP tools first if installed (graph query, symbol search, impact analysis — e.g. Cortex). Purpose-built retrieval beats raw grep; counts as exploration.
  2. Candidate files: Claude Glob (**/*auth*, src/**/*.ts) or Codex rg --files -g '*auth*'.
  3. Shortlist text hits: Claude Grep -l or Codex rg -l.
  4. Context hits: Claude Grep -n -C 3 or Codex rg -n -C 3. Search declaration patterns (def X, class X, func X, X =) not bare name.
  5. Read narrow: Claude Read offset/limit or Codex bounded shell reads (sed -n 'START,ENDp'). Full read only when file <200 lines.

Rules:

  • Batch independent searches in one tool block — parallel, one round-trip.
  • Before changing symbol: grep ALL usages, not just definition. Callers break silently otherwise.
  • Wrong-looking grep results: widen pattern once, then try Glob on filenames. Two dead ends = rethink term, don't brute-force variants.
  • Never read a whole file to "get context" when search can locate. Full-file reads are the #1 token leak.
  • Record what you learned in one line before moving on (file:line of target, usage count).

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