Index of every page on this site: llms.txt
All skills
juliusbrussee avatar

/caveman-learn

@bad48a0
by Julius Brusseejuliusbrussee/caveman114k stars
6,594
Run it yourself

Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.

Use this Skill: https://skilld.dev/gh/juliusbrussee/caveman/caveman-learn

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

CLAUDE.md

≈472 tokens on demand. Your agent reads this file only when SKILL.md points to it.

skills/caveman-learn — the Caveman Learn editing skill (Apache-2.0, public)

The consent-gated half of caveman learn. The analyzer (the Go proxy) measures where an agent's tokens go and writes a ranked plan; this skill is what an agent loads to act on that plan — proposing each fix and applying it only with the user's per-edit yes. It is the loop-closer the learn spec §10 describes, plus the new cavemem_offload move.

Layout

  • SKILL.md — the canonical skill body (frontmatter name: caveman-learn + a trigger-phrase description; body = the read-plan → per-class consent loop). This file is the source of truth.
  • tests/skill-file.test.mjs — asserts the canonical file is well-formed and honest (frontmatter present; the net-token-negative gate, the never-make-the-agent-dumber guard, consent-per-edit, and reversibility are all stated; no imperative for behavioral findings; no placeholders).

Install path

caveman tools skills install caveman-learn (in ../../cli/src/index.ts) writes this file into a repo's .claude/skills/caveman-learn/SKILL.md (Claude Code) or ~/.codex/skills/caveman-learn/SKILL.md (Codex). The CLI embeds a byte-identical copy (CAVEMAN_LEARN_SKILL_MD) because the published CLI ships no sibling assets; ../../cli/tests/skills.runtime.mjs asserts the embedded copy equals this canonical file (the drift guard). Change this file and that constant together.

Boundary (binding)

The skill — using the agent's own file tools — is the ONLY thing that edits a user's config. caveman learn apply stays read-only (it materializes candidates), and caveman mem * are mechanical store ops. The offload move enforces a net-token-negative gate and the never-make-the-agent-dumber guard before any trim.

See ../../mem/CLAUDE.md (cavemem) · ../caveman-explore/SKILL.md (the packaging precedent)

Source: SKILL.md on GitHub

Skill behaviors

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

Third-party checks

No alerts7d3 checks · Risk SAFE
  • Gen Agent Trust Hub7d

    The skill is a token optimization tool designed to reduce an AI agent's token usage by analyzing performance reports and suggesting fixes. It demonstrates high security standards by requiring explicit user consent for every file modification, verifying content integrity using SHA256 hashes before processing, and implementing a 'net-token-negative' gate that reverts any changes that do not measurably improve efficiency.

  • Socket7d

    No alerts

  • Snyk7d

    Risk: LOW · No issues

Provenance

Signed by skilld at bad48a0. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated last week

README badge

README badge for juliusbrussee/caveman/caveman-learn