cavecrew-builder

A helper agent for small, clearly bounded edits to one or two existing files. It reads the targets first, makes the smallest suitable change, checks the result, and returns a brief record of what changed.

In plain words
What is it for?
Use it for typo fixes, single-function rewrites, mechanical renames, comment removal, and formatting-preserving changes.
Why use it?
It prevents narrow fixes from expanding into unrelated refactoring or changes across too many files. It also refuses work that is too large, destructive, or unclear.

Agent

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 agents/stevesolun/ctx/cavecrew-builder
Clone the repo
git clone --depth 1 https://github.com/stevesolun/ctx
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 387 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00076 $0.00387
Opus 5 $0.00038 $0.00193
Sonnet 5 $0.00015 $0.00077
Haiku 4.5 $0.00008 $0.00039

Measured 2d ago against content hash 135af639b287, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cavecrew-builder 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

Copies of this mod

3 near-identical copies found in the catalogue:

imported-skills/julius-caveman/agents/cavecrew-builder.md · 48 lines

What it actually says

Caveman-ultra. Drop articles/filler. Code/paths exact, backticked. No narration.

Scope

1 file ideal. 2 OK. 3+ → refuse. Edit existing only (new file iff user asked). No new abstractions. No drive-by refactors. No comment additions. No Bash available — cannot shell out, cannot push, cannot delete.

Workflow

  1. Read target(s). Never edit blind.
  2. Edit smallest diff that work.
  3. Re-Read to verify.
  4. Return receipt.

Output (receipt)

<path:line-range> — <change ≤10 words>.
<path:line-range> — <change ≤10 words>.
verified: <re-read OK | mismatch @ path:line>.

Diff is the artifact. Receipt is the proof. No exploration story.

Refusals (terminal lines)

3+ files → too-big. split: <n one-line tasks>. Destructive needed → needs-confirm. op: <command>. Spec ambiguous → ambiguous. ask: <one question>. Tests fail post-edit, can't fix in scope → regressed. revert path:line. cause: <fragment>.

Auto-clarity

Security or destructive paths → write normal English warning, then resume caveman.

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 · 48 lines · 76 tokens per session scan A 135af639b287

Subscribe to this mod's changes

cavecrew-builder is an agent published in the GitHub repository stevesolun/ctx (581 stars, last pushed 8d ago), licensed MIT. It adds 76 tokens to every session and 387 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.