agentleFS
jakkarin-promseejakkarin-promsee/my-harness/.claude/skills/explore/SKILL.md

explore

Skill1 starsChanged 4 months agoMITView on GitHub

Understand a part of the researcher-harness before changing it. Use when starting work on an unfamiliar module (the loop, a provider, a tool, permissions, sessions, the CLI) and you need to know how it works and why — without editing anything yet.

69 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

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 60 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Start at the map: Read src/harness/CLAUDE.md (auto-loaded when you open code) for the architecture-in-brief and the invariants you must not …

    line 12
  2. Very specific:

    Read the code's own words: Every module's top docstring is the spec (loop.py, base.py, subagent.py …).

    line 15
  3. Distinctive:

    Code is the territory: If a README or note disagrees with the code, trust the code and flag the stale doc.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 60 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 a part of the harness

Goal: build an accurate mental model of one area before touching it, using the context hierarchy so you read the right things in the right order — not the whole repo (that waste is the project's Pain 1).

Steps

  1. Start at the map. Read src/harness/CLAUDE.md (auto-loaded when you open code) for the architecture-in-brief and the invariants you must not break.
  2. Find the folder. Open the README.md in the folder you're exploring (src/harness/core/, providers/, tools/, or tests/, acceptance/). It's the file-by-file map of what's there now, with a link to the design note.
  3. Read the why. Open the linked docs/notes/NN-*.md. Notes are written before implementing: what the seniors do → what we built → how we know it works.
  4. Read the code's own words. Every module's top docstring is the spec (loop.py, base.py, subagent.py …). Read it before the body.
  5. Run it, for free. Offline: uv run pytest -q. Live behavior on the local model costs $0: uv run harness ollama.

Rules

  • Read narrowly. The whole point of the hierarchy is that understanding one part shouldn't require the whole repo in context.
  • Don't edit in this mode. Explore produces understanding; the implement-feature skill produces changes.
  • Code is the territory. If a README or note disagrees with the code, trust the code and flag the stale doc.

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.