Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Decision guide for delegating to caveman-style subagents. An agent skill from vishiri/fantasia-archive.
Install Cavecrew
$ npx skills add vishiri/fantasia-archive --skill cavecrew -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install vishiri/fantasia-archive cavecrew --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/vishiri/fantasia-archive.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/cavecrew .claude/skills/cavecrew && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "cavecrew" agent skill from https://github.com/vishiri/fantasia-archive/tree/master/.agents/skills/cavecrew into .claude/skills/cavecrew/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cavecrew", 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.
$skill-installer install https://github.com/vishiri/fantasia-archive/tree/master/.agents/skills/cavecrewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add vishiri/fantasia-archive --skill cavecrew -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install vishiri/fantasia-archive cavecrew --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vishiri/fantasia-archive.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/cavecrew .agents/skills/cavecrew && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cavecrew" agent skill from https://github.com/vishiri/fantasia-archive/tree/master/.agents/skills/cavecrew into .agents/skills/cavecrew/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cavecrew", 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 vishiri/fantasia-archive --skill cavecrew -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install vishiri/fantasia-archive cavecrew --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vishiri/fantasia-archive.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/cavecrew .cursor/skills/cavecrew && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cavecrew" agent skill from https://github.com/vishiri/fantasia-archive/tree/master/.agents/skills/cavecrew into .cursor/skills/cavecrew/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cavecrew", 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.
$ gemini skills install https://github.com/vishiri/fantasia-archive.git --path .agents/skills/cavecrew--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add vishiri/fantasia-archive --skill cavecrew -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install vishiri/fantasia-archive cavecrew --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vishiri/fantasia-archive.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/cavecrew .gemini/skills/cavecrew && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cavecrew" agent skill from https://github.com/vishiri/fantasia-archive/tree/master/.agents/skills/cavecrew into .gemini/skills/cavecrew/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cavecrew", 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 vishiri/fantasia-archive cavecrewInstalls 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 vishiri/fantasia-archive --skill cavecrew -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/vishiri/fantasia-archive.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/cavecrew .github/skills/cavecrew && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cavecrew" agent skill from https://github.com/vishiri/fantasia-archive/tree/master/.agents/skills/cavecrew into .github/skills/cavecrew/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cavecrew", 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 vishiri/fantasia-archive --skill cavecrew -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install vishiri/fantasia-archive cavecrew --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vishiri/fantasia-archive.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/cavecrew .opencode/skills/cavecrew && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cavecrew" agent skill from https://github.com/vishiri/fantasia-archive/tree/master/.agents/skills/cavecrew into .opencode/skills/cavecrew/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cavecrew", 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.
Facts
- Skill name
cavecrew- GitHub stars
- 409
- Used in
- 7 other repos
- Token cost
- ~1k tokens
- SKILL.md length
- 415 words
- Files
- 2
- Skills in repo
- 35
- Repo updated
- First seen
- Licence
- GPL-3.0
At a glance
Decision guide for delegating to caveman-style subagents. An agent skill from vishiri/fantasia-archive.
- Works in 3 steps: cavecrew-investigator returns site list. → Main thread picks 1-2 sites, hands paths… → cavecrew-reviewer audits the diff.
- Tasks that involve Subagents
- SKILL.md covers When to use cavecrew vs…, Why this exists (the real win), Output contracts and Chaining patterns, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Cavecrew is an agent skill from vishiri/fantasia-archive. Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn cavecrew-investigator (locate code), cavecrew-builder (1-2 file edit), or cavecrew-reviewer (diff review) instead of doing the work inline or using vanilla Explore. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context"…
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `README.md`).
It sits in Agent Workflows, covering Subagents. The repository describes itself as: A world-builder's best friend! The licence is GPL-3.0.
When your agent uses it
- Tasks that involve Subagents
Example prompts
- “delegate to subagent”
- “use cavecrew”
- “spawn investigator/builder/reviewer”
- “/cavecrew”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- cavecrew-investigator returns site list.
- Main thread picks 1-2 sites, hands paths to cavecrew-builder.
- cavecrew-reviewer audits the diff.
What it can do on your machine
Read from SKILL.md and the folder at commit 26d4648. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Cavecrew loads about 1k tokens when it runs. Until then it costs about 140 tokens; SKILL.md has 415 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.
Safety
Auto-check passed
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.
SKILL.md
The full file from vishiri/fantasia-archive at commit 26d4648, republished under its GPL-3.0 licence (© vishiri). 415 words, ~1,034 tokens.
Download SKILL.mdSave it as
.claude/skills/cavecrew/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- cavecrew
- description
- Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".
Cavecrew = three subagent presets that emit caveman output. Same job as Anthropic defaults (Explore, edit-style agents, reviewer); difference is the tool-result they return is compressed, so main context shrinks per delegation.
Model: every cavecrew / Task spawn must follow subagent-model-policy.mdc — cursor-grok-4.7-high when allowed; never Fast (composer-2.5-fast or any *fast* slug).
When to use cavecrew vs alternatives
| Task | Use |
|---|---|
| "Where is X defined / what calls Y / list uses of Z" | cavecrew-investigator |
| Same but you also want suggestions/architecture commentary | Explore (vanilla) |
| Surgical edit, ≤2 files, scope obvious | cavecrew-builder |
| New feature / 3+ files / cross-cutting refactor | Main thread or feature-dev:code-architect |
| Review diff, branch, or file for bugs | cavecrew-reviewer |
| Deep code review with rationale + alternatives | Code Reviewer (vanilla) |
| One-line answer you already know | Main thread, no subagent |
Rule of thumb: if you'd want the subagent's output in 1/3 the tokens, pick cavecrew. If you'd want prose, pick vanilla.
Why this exists (the real win)
Subagent tool results get injected into main context verbatim. A vanilla Explore that returns 2k tokens of prose costs 2k tokens of main-context budget every time. The same finding from cavecrew-investigator returns ~700 tokens. Across 20 delegations in one session that's the difference between context exhaustion and finishing the task.
Output contracts
What main thread can rely on per agent:
cavecrew-investigator
<Header>:
- path:line — `symbol` — short note
totals: <counts>.Or No match. Always file-path-first, line-number-attached, backticked symbols. Safe to grep with path:\d+.
cavecrew-builder
<path:line-range> — <change ≤10 words>.
verified: <re-read OK | mismatch @ path:line>.Or one of: too-big. / needs-confirm. / ambiguous. / regressed. (terminal first token).
cavecrew-reviewer
path:line: <emoji> <severity>: <problem>. <fix>.
totals: N🔴 N🟡 N🔵 N❓Or No issues. Findings sorted file → line ascending.
Show full SKILL.md (173 more words)Show less
Chaining patterns
Locate → fix → verify (most common):
cavecrew-investigatorreturns site list.- Main thread picks 1-2 sites, hands paths to
cavecrew-builder. cavecrew-revieweraudits the diff.
Parallel scout (when investigation is broad):
Spawn 2-3 cavecrew-investigator calls in one message (different angles: defs vs callers vs tests). Aggregate in main thread.
Single-shot edit (when site is already known):
Skip investigator. Hand exact path:line to cavecrew-builder directly.
What NOT to do
- Don't use
cavecrew-builderwhen you don't already know the file. Spawn investigator first or main thread will eat tokens passing context. - Don't chain
cavecrew-investigator → cavecrew-builderfor a 5-file refactor. Builder will returntoo-big.and you'll have wasted a turn. - Don't ask
cavecrew-reviewerfor "general feedback" — it returns findings only, no architecture opinions. UseCode Reviewerfor that. - Don't expect prose. Cavecrew output is structured, sometimes terse to the point of cryptic. If a human will read it directly, paraphrase.
Auto-clarity (inherited)
Subagents drop caveman → normal English for security warnings, irreversible-action confirmations, and any output where fragment ambiguity could be misread. Resume caveman after.
© vishiri, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .agents/skills/cavecrew of vishiri/fantasia-archive.
- SKILL.md
- README.md
Open the folder on GitHubat commit 26d4648
Used in 7 other repositories
We found 8 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 7 other GitHub owners. This page covers the copy in vishiri/fantasia-archive, which our catalogue first saw on October 7, 2026.
- goern/forgejo-mcp.agents/skills/cavecrew
- kubestellar/console.agents/skills/cavecrew
- JuliusBrussee/cavemanskills/cavecrewplugins/caveman/skills/cavecrew
- stevesolun/ctximported-skills/julius-caveman/skills/cavecrew
- codejunkie99/agentic-stack.cursor/skills/cavecrew
- shortcuts/locationjoystick.agents/skills/cavecrew
- aiskillstore/marketplaceskills/juliusbrussee/cavecrew
Compare with similar skills
Cavecrew 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 |
|---|---|---|---|---|---|---|
| Cavecrew this skillvishiri/fantasia-archive | 409 | 7 repos | ~1k | Automated safety check: Pass | GPL-3.0 | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 7 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 37 repos | ~1.2k | Automated safety check: Pass | None | |
| Dispatching Parallel Agentsultralisp/ultralisp | 258 | 40 repos | ~1.5k | Automated safety check: Pass | None | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~12k | Automated safety check: Pass | CC-BY-4.0 |
Similar skills
- Official
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Dispatching Parallel Agents
ultralisp/ultralisp
A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Paseo Advisor Second Opinion
getpaseo/paseo
Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
More from vishiri/fantasia-archive
All 35 skills in this repoCaveman Commit
vishiri/fantasia-archive
Ultra-compressed commit message generator. An agent skill from vishiri/fantasia-archive.
Caveman Review
vishiri/fantasia-archive
Ultra-compressed code review comments. An agent skill from vishiri/fantasia-archive.
Caveman Compress
vishiri/fantasia-archive
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
Caveman Help
vishiri/fantasia-archive
Quick-reference card for all caveman modes, skills, and commands.
Fantasia Context Menu Dividers
vishiri/fantasia-archive
Context menu divider policy: full primary-bright group separators vs low-opacity separatorAlt between consecutive items in the same group.
Fantasia Dev Setup
vishiri/fantasia-archive
Sets up and runs Fantasia Archive locally using Yarn, Node.js 22.22 or newer, and Quasar Electron mode.
Related
Categories
Questions about Cavecrew
What does Cavecrew do?
Decision guide for delegating to caveman-style subagents. An agent skill from vishiri/fantasia-archive. Cavecrew is an agent skill from vishiri/fantasia-archive. Decision guide for delegating to caveman-style subagents.
When should I use Cavecrew?
Cavecrew fits situations like: tasks that involve Subagents.
How do I install Cavecrew in Claude Code?
Run `npx skills add vishiri/fantasia-archive --skill cavecrew -a claude-code`. Or copy the skill folder (.agents/skills/cavecrew in vishiri/fantasia-archive) into .claude/skills/cavecrew in your project. Claude Code loads it when a task matches its description.
How do I install Cavecrew in Codex?
Run `npx skills add vishiri/fantasia-archive --skill cavecrew -a codex`. Or copy the skill folder (.agents/skills/cavecrew in vishiri/fantasia-archive) into .agents/skills/cavecrew in your project. Codex loads it when a task matches its description.
Can I use Cavecrew in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vishiri/fantasia-archive --skill cavecrew -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cavecrew, .gemini/skills/cavecrew, .github/skills/cavecrew and .opencode/skills/cavecrew in your project.
What does Cavecrew need to run?
SKILL.md names no scripts, command-line tools or credentials: Cavecrew is instructions for the agent only.
Does Cavecrew access the network?
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.
Is Cavecrew safe to install?
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.
What licence does Cavecrew use?
Cavecrew is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Cavecrew use?
About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Cavecrew?
Skills that share tags, products or a category with Cavecrew: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Cavecrew?
vishiri (a GitHub user) maintains it in vishiri/fantasia-archive, which has 409 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on October 7, 2026.
Source: vishiri/fantasia-archive on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.