Cavecrew

cavecrew

Delegate code tasks to compressed subagents that shrink context by ~60% per delegation.

juliusbrussee/caveman·335.7Kinstalls109.9Kstars

SKILL.md

Full skill instructions

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.

Install skill

Copy and run in your terminal

npx -y skills add https://github.com/juliusbrussee/caveman --skill cavecrew

View on GitHub

cavecrew

caveman
Ultra-compressed communication mode cutting token usage ~75% while preserving technical accuracy.
559K installs
caveman-commit
Terse, conventional commit messages that prioritize reasoning over description.
392.8K installs
caveman-review
Ultra-compressed code review comments: location, problem, fix on one line each.
388.8K installs
caveman-compress
Compress natural language memory files into caveman-speak to reduce input tokens.
387.7K installs

More skills from juliusbrussee

juliusbrussee/caveman

caveman-help

Quick-reference card for caveman modes, skills, and commands with one-shot display.

109.9K 379.4K

View

juliusbrussee/caveman

caveman-stats

Real token usage and estimated savings metrics from your Claude Code session log.

109.9K 334.9K

View

juliusbrussee/caveman

compress

Compress natural language memory files into caveman-speak to reduce input tokens.

109.9K 46.9K

View

juliusbrussee/skills

caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

160 3.5K

View

juliusbrussee/cavekit

caveman

1.1K 2.8K

View

juliusbrussee/cavekit

build

1.1K 2.7K

View

juliusbrussee/cavekit

spec

1.1K 2.7K

View

juliusbrussee/cavekit

check

1.1K 2.7K

View

juliusbrussee/cavekit

backprop

1.1K 2.6K

View

juliusbrussee/skills

grill-me

Calibrated grilling session for stress-testing a plan, design, idea, or decision. First assesses the user's topic knowledge, confidence, and desired pressure level, then asks one question at a time with recommended answers. Use when user says "grill me", "stress-test this", "challenge my plan", "interview me", or wants a plan probed without being overwhelmed.

160 2.6K

View

juliusbrussee/skills

junior-to-senior

Adversarial senior-engineer review for agent-generated plans, designs, and architectures. Treats the current output as junior work, constructs a senior reviewer whose domain expertise comes from live codebase research plus web research of current best practices, diagnoses altitude failures (too vague or too granular), then rewrites the plan into a scoped, state-of-the-art version. Use when the user says "junior to senior", "senior review", "review this like a staff engineer", when a plan feels hand-wavy or lost in details, or before committing to any agent-written plan.

160 2.5K

View

juliusbrussee/skills

interface-kit

Authoritative guide for implementing stunning, accessible, performant UI. Synthesizes design engineering philosophy, accessibility standards, animation principles, spatial design, typography, color systems, and component craft into a single actionable reference. Complements the design-system skill (which covers DESIGN.md spec writing) by covering the HOW of implementation. Trigger phrases: "build UI", "create component", "landing page", "make it look good", "frontend", "design", "polish UI", "implement design", "make it beautiful", "UI implementation", "component styling", "animation", "accessibility"

160 2.1K

View