cavecrew

A guide for deciding when to delegate coding work to short-answer helper agents called cavecrew investigators, builders, or reviewers.

In plain words
What is it for?
It is for choosing helpers to locate code, make small edits in up to two files, or review a diff, while leaving larger features and cross-cutting changes to the main agent.
Why use it?
It prevents using the wrong kind of helper for a task and keeps delegated findings concise.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/kubestellar/console/cavecrew
Any agent
npx skills add kubestellar/console --skill cavecrew
Clone the repo
git clone --depth 1 https://github.com/kubestellar/console

Made for: Claude Code, Codex.

Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 984 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00134 $0.00984
Opus 5 $0.00067 $0.00492
Sonnet 5 $0.00027 $0.00197
Haiku 4.5 $0.00013 $0.00098

Measured 2d ago against content hash b74f374f6aae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cavecrew scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to cavecrew — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/cavecrew/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

Read the full file on GitHub · 83 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 83 lines · 134 tokens per session scan A b74f374f6aae

Subscribe to this mod's changes

cavecrew is a skill published in the GitHub repository kubestellar/console (130 stars, last pushed 2d ago), licensed Apache-2.0. It adds 134 tokens to every session and 984 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to cavecrew, differing in 0 lines, and is treated as a copy.