kubestellarkubestellar/console/.agents/skills/cavecrew/SKILL.md

cavecrew

Skill144 starsChanged 3 months agoApache-2.0View on GitHub

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".

We split this skill into the rules it gives an agent

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

1
Common
Most of the 14 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Don't use cavecrew-builder when you don't already know the file.
line 75
Very specific:
Don't chain cavecrew-investigator → cavecrew-builder for a 5-file refactor.
line 76
Very specific:
Don't ask cavecrew-reviewer for "general feedback" — it returns findings only, no architecture opinions.
line 77
Common:
Don't expect prose. Cavecrew output is structured, sometimes terse to the point of cryptic.
line 78

“Common” is measured: kept by at least 6 in 10 of the 14 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

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.

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.

Chaining patterns

Locate → fix → verify (most common):

cavecrew-investigator returns site list.
Main thread picks 1-2 sites, hands paths to cavecrew-builder.
cavecrew-reviewer audits 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-builder when you don't already know the file. Spawn investigator first or main thread will eat tokens passing context.
Don't chain cavecrew-investigator → cavecrew-builder for a 5-file refactor. Builder will return too-big. and you'll have wasted a turn.
Don't ask cavecrew-reviewer for "general feedback" — it returns findings only, no architecture opinions. Use Code Reviewer for 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.

Download now (ZIP)

Other versions40 projects use a version of this.
Word for word · 23
dbt-labs/docs.getdbt.com★ 219100% same
Namma-Flutter/namma_wallet★ 59100% same
rawsun007/claude-notch★ 59100% same
nitingupta220/riperflow★ 19100% same
chinkan/RustFox★ 9100% same
CashewTeam/Con11-AI-Skills★ 8100% same
Youngmaidainon/Agent-Level-Up★ 3100% same
abhinavteja123/codemore★ 2100% same
RainMT-dv/skills-pack★ 2100% same
srv1n/rzn-browser★ 2100% same
13 more not listed
Edited · 17
JuliusBrussee/caveman★ 115k86% same
codejunkie99/agentic-stack★ 2.3k93% same
goern/forgejo-mcp★ 14695% same
codejunkie99/agentic-stack-desktop★ 5993% same
chadixearth/graphyloop★ 3100% same
Hayatelin/caveman-zh-CN★ 212% same
hongphuc5497/skills★ 286% same
john-data-chen/hermes-agent-backup★ 2100% same
nomdedev/agent-manager-template★ 295% same
agrivisionai/claude-skills★ 199% same
7 more not listed
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use ponytail-help, image-to-code and 10 more.
Other files people use alongside this one.
- GoogleSkill
  ponytail-help
  Quick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail".
  Also in 4 projects that use this
- OpenAISkill
  image-to-code
  Implement a selected image, screenshot, mockup, or Image Gen reference as a faithful, responsive frontend.
  Also in 5 projects that use this
- GoogleSkill
  ponytail
  Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).
  Also in 7 projects that use this
- AnasX7Skill
  minimalist-ui
  Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.
  Also in 5 projects that use this
- HK-hubSkill
  stitch-design-taste
  Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
  Also in 4 projects that use this
- AnasX7Skill
  full-output-enforcement
  Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
  Also in 4 projects that use this
- +4 more from google
- +2 more from AnasX7
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/caveman.mdcCursor rule
- caveman-commitSkill
- caveman-compressSkill
- caveman-helpSkill
- caveman-reviewSkill
- cavemanSkill
- caveman-statsSkill

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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.

Check your setup, free

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

When to use cavecrew vs alternatives

Why this exists (the real win)

Output contracts

Chaining patterns

What NOT to do

Auto-clarity (inherited)

Trending

Word for word · 23

Edited · 17

Wrote their own version · 0

ponytail-help

image-to-code

ponytail

minimalist-ui

stitch-design-taste

full-output-enforcement

Does it work?

Your trail

Now do this for your own.