One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
JuliusBrusseeAGENTS.mdJuliusBrussee/caveman/AGENTS.md
Read CLAUDE.md before repository work. Binding routing: this repo owns skills, Engine, and MV3 extension; Agent SDK work belongs in /Users/julb/Desktop/GitHub/caveman-agent-sdk; Browse driver/MCP/benchmark/plugin work belongs in /Users/julb/Desktop/GitHub/caveman-browse; proprietary Pebble product…
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/browse/CLAUDE.md
Repository routing: do not continue Browse product work here. Source of truth is JuliusBrussee/caveman-browse, local checkout /Users/julb/Desktop/GitHub/caveman-browse. This directory is a consumer copy; edit only for pinned integration, migration/removal, or…
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/CLAUDE.md
README = product front door. Non-technical people read it to decide if caveman worth install. Treat like UI copy. Rules for any README change: Caveman makes AI coding agents respond…
JuliusBrusseeAGENTS.mdJuliusBrussee/caveman/engine/AGENTS.md
Detect a payload's type → route to a safety-classed compressor → count the token reduction → store the original for recovery. The stable four-call API (Compress/Retrieve/Detect/Stats) is what the proxy,…
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/engine/CLAUDE.md
Detect a payload's type → route to a safety-classed compressor → count the token reduction → store the original for recovery. The stable four-call API (Compress/Retrieve/Detect/Stats) is what the proxy,…
JuliusBrusseeAGENTS.mdJuliusBrussee/caveman/extension/AGENTS.md
The consumer top-of-funnel: a toggle that, on ChatGPT / Claude / Gemini, prepends the caveman skill directive to each message you send and re-fires the send, so the AI replies…
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/integrations/CLAUDE.md
Declarative routing recipes for AI SDKs/frameworks: each recipe is the one-line base-URL shape that points a framework at the byte-safe gateway, with {{baseURL}} (gateway origin) and {{app}} (the /w/<app> attribution…
JuliusBrusseeAGENTS.mdJuliusBrussee/caveman/mcp/AGENTS.md
A thin stdio JSON-RPC adapter exposing the compression engine as five MCP tools to any host (Claude Code, Cursor, …). It owns only the MCP framing; all compression is the…
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/mcp/CLAUDE.md
A thin stdio JSON-RPC adapter exposing the compression engine as five MCP tools to any host (Claude Code, Cursor, …). It owns only the MCP framing; all compression is the…
JuliusBrusseeAGENTS.mdJuliusBrussee/caveman/mem/AGENTS.md
Durable, cross-session memory: remember / recall / supersede / history / forget. A local SQLite store holds the raw memories (the source of truth); recall ranks them with deterministic BM25…
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/mem/CLAUDE.md
Durable, cross-session memory: remember / recall / supersede / history / forget. A local SQLite store holds the raw memories (the source of truth); recall ranks them with deterministic BM25…
JuliusBrusseeAGENTS.mdJuliusBrussee/caveman/proxy/AGENTS.md
A base-URL-swap reverse proxy: match → authenticate → inspect → byte-safe transform → upstream → meter. Single-operator, BYOK, zero cloud dependencies. It shares its provider adapters with the managed gateway…
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/proxy/CLAUDE.md
A base-URL-swap reverse proxy: match → authenticate → inspect → byte-safe transform → upstream → meter. Single-operator, BYOK, zero cloud dependencies. It shares its provider adapters with the managed gateway…
JuliusBrusseeAGENTS.mdJuliusBrussee/caveman/shrink/AGENTS.md
Compress MCP/OpenAI tool definitions before they fill the context window. A thin Go wrapper over the engine's toolschema compressor: it drops annotation metadata (examples, titles, $comment, $schema) and reduces long…
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/shrink/CLAUDE.md
Compress MCP/OpenAI tool definitions before they fill the context window. A thin Go wrapper over the engine's toolschema compressor: it drops annotation metadata (examples, titles, $comment, $schema) and reduces free-text…
JuliusBrusseeSkillJuliusBrussee/caveman/skills/cavecrew/SKILL.md
When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.
JuliusBrusseeSkillJuliusBrussee/caveman/skills/caveman-commit/SKILL.md
Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
JuliusBrusseeSkillJuliusBrussee/caveman/skills/caveman-compress/SKILL.md
Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /caveman-compress.
JuliusBrusseeSkillJuliusBrussee/caveman/skills/caveman-discover/SKILL.md
Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.
JuliusBrusseeSkillJuliusBrussee/caveman/skills/caveman-evidence-review/SKILL.md
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
