Caveman Learn Token Fixes
JuliusBrussee/caveman
Acts on a Caveman learn report: reviews ranked token sinks, applies cost-lowering edits one at a time with your consent, and reports what each fix returned.
A skill your agent uses when maintaining or optimizing OpenClaw workspace files — AGENTS.md, TOOLS.md, SOUL.md, USER.md, IDENTITY.md, HEARTBEAT.md, BOOT.md, MEMORY.md, and related checklists and…
$ npx skills add win4r/openclaw-workspace --skill openclaw-workspace -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install win4r/openclaw-workspace openclaw-workspace --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "openclaw-workspace" agent skill from https://github.com/win4r/openclaw-workspace/tree/main into .claude/skills/openclaw-workspace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclaw-workspace", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add win4r/openclaw-workspace --skill openclaw-workspace -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install win4r/openclaw-workspace openclaw-workspace --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "openclaw-workspace" agent skill from https://github.com/win4r/openclaw-workspace/tree/main into .agents/skills/openclaw-workspace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclaw-workspace", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add win4r/openclaw-workspace --skill openclaw-workspace -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install win4r/openclaw-workspace openclaw-workspace --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "openclaw-workspace" agent skill from https://github.com/win4r/openclaw-workspace/tree/main into .cursor/skills/openclaw-workspace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclaw-workspace", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add win4r/openclaw-workspace --skill openclaw-workspace -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install win4r/openclaw-workspace openclaw-workspace --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "openclaw-workspace" agent skill from https://github.com/win4r/openclaw-workspace/tree/main into .gemini/skills/openclaw-workspace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclaw-workspace", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install win4r/openclaw-workspace openclaw-workspaceInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add win4r/openclaw-workspace --skill openclaw-workspace -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "openclaw-workspace" agent skill from https://github.com/win4r/openclaw-workspace/tree/main into .github/skills/openclaw-workspace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclaw-workspace", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add win4r/openclaw-workspace --skill openclaw-workspace -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install win4r/openclaw-workspace openclaw-workspace --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "openclaw-workspace" agent skill from https://github.com/win4r/openclaw-workspace/tree/main into .opencode/skills/openclaw-workspace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclaw-workspace", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
openclaw-workspaceA skill your agent uses when maintaining or optimizing OpenClaw workspace files — AGENTS.md, TOOLS.md, SOUL.md, USER.md, IDENTITY.md, HEARTBEAT.md, BOOT.md, MEMORY.md, and related checklists and…
Openclaw Workspace is an agent skill from win4r/openclaw-workspace. Use when maintaining or optimizing OpenClaw workspace files — AGENTS.md, TOOLS.md, SOUL.md, USER.md, IDENTITY.md, HEARTBEAT.md, BOOT.md, MEMORY.md, and related checklists and memory files. Covers workspace auditing, token budget analysis, new agent workspace setup from scratch, memory distillation, and cross-file consistency reviews.
Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `README.md`, `README_CN.md` and `references/optimization-guide.md`).
It sits in Agent Workflows, covering LLM cost and token optimization and Agent instruction files. The repository describes itself as: Claude Code skill for maintaining and optimizing OpenClaw workspace files (AGENTS.md, SOUL.md, TOOLS.md, MEMORY.md, checklists).
7 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 4e81a91. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and bash).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Openclaw Workspace loads about 2.4k tokens when it runs, and up to ~7.7k if it reads all its reference files. Until then it costs about 89 tokens; SKILL.md has 1,063 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
Without a licence we can't republish the file, so here is its outline and opening line. It has 1,063 words (~2,429 tokens).
“OpenClaw workspace files form the agent's "soul and memory" — they are injected into the system prompt on every turn (or on relevant turns), giving the agent its identity, behavioral rules, environmental knowledge, and long-term memory. Managing these files well…”
SKILL.md and 4 other files (references) in the repository root of win4r/openclaw-workspace.
Open the folder on GitHubat commit 4e81a91
Openclaw Workspace next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Openclaw Workspace this skillwin4r/openclaw-workspace | 288 | — | ~2.4k | Automated safety check: Pass | None | |
| Caveman Learn Token FixesJuliusBrussee/caveman | 111k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Context Budget Checkposhan0126/dotclaude | 871 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Claude Code Cost Optimizermergisi/awesome-openclaw-agents | 4k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Caveman Memory File CompressorJuliusBrussee/caveman-code | 942 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Claude Code Masteryborghei/Claude-Skills | 886 | — | ~1.9k | Automated safety check: Pass | MIT |
JuliusBrussee/caveman
Acts on a Caveman learn report: reviews ranked token sinks, applies cost-lowering edits one at a time with your consent, and reports what each fix returned.
poshan0126/dotclaude
Estimates the per-turn token cost of a project's .claude folder and CLAUDE.md, split into always-loaded, path-scoped and invoked-only files, and flags what runs over budget.
mergisi/awesome-openclaw-agents
Audits a project's Claude Code setup for common token-cost leaks and returns a prioritized fix list, using only static inspection of files and settings.
JuliusBrussee/caveman-code
Rewrites a memory file such as CLAUDE.md or a todo list in terse caveman-style text to cut input tokens, saving a readable backup outside the project tree.
borghei/Claude-Skills
A skill your agent uses when the user asks to "optimize CLAUDE.md", "create a new skill", "write a custom agent", "configure hooks", "manage context window", "set up MCP servers", "scaffold a skill…
haru/redmine_ai_helper
Toggle a project-local concise-output directive that suppresses agent prose padding during SDD steps.
Categories
A skill your agent uses when maintaining or optimizing OpenClaw workspace files — AGENTS.md, TOOLS.md, SOUL.md, USER.md, IDENTITY.md, HEARTBEAT.md, BOOT.md, MEMORY.md, and related checklists and…. Openclaw Workspace is an agent skill from win4r/openclaw-workspace.md, and related checklists and memory files.
Openclaw Workspace fits situations like: optimizing OpenClaw workspace files — AGENTS.md; related checklists and memory files.
Run `npx skills add win4r/openclaw-workspace --skill openclaw-workspace -a claude-code`. Or copy the skill folder (the win4r/openclaw-workspace repository) into .claude/skills/openclaw-workspace in your project. Claude Code loads it when a task matches its description.
Run `npx skills add win4r/openclaw-workspace --skill openclaw-workspace -a codex`. Or copy the skill folder (the win4r/openclaw-workspace repository) into .agents/skills/openclaw-workspace in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add win4r/openclaw-workspace --skill openclaw-workspace -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openclaw-workspace, .gemini/skills/openclaw-workspace, .github/skills/openclaw-workspace and .opencode/skills/openclaw-workspace in your project.
SKILL.md names no scripts, command-line tools or credentials: Openclaw Workspace is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
No licence was found for Openclaw Workspace or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
About 2.4k tokens (SKILL.md is roughly 9.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.3k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Openclaw Workspace: Caveman Learn Token Fixes (JuliusBrussee/caveman, 111k stars), Context Budget Check (poshan0126/dotclaude, 871 stars), Claude Code Cost Optimizer (mergisi/awesome-openclaw-agents, 4k stars) and Caveman Memory File Compressor (JuliusBrussee/caveman-code, 942 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
win4r (a GitHub user) maintains it in win4r/openclaw-workspace, which has 288 GitHub stars. The repository was last updated on March 11, 2026.
Source: win4r/openclaw-workspace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.