.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/caveman/cavecrew-builder
home/subagents/juliusbrussee/caveman/cavecrew-builder
juliusbrussee avatar

cavecrew-builder

byjuliusbrussee· 6 subagents

Stars

93k

Forks

5.3k

Category

Productivity & Workflow

View on GitHub

TL;DR

Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns caveman diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or

How to install cavecrew-builder?

juliusbrussee/caveman/cavecrew-builder
$curl -o .claude/agents/cavecrew-builder.md https://raw.githubusercontent.com/juliusbrussee/caveman/HEAD/agents/cavecrew-builder.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install cavecrew-builder by running `curl -o .claude/agents/cavecrew-builder.md https://raw.githubusercontent.com/juliusbrussee/caveman/HEAD/agents/cavecrew-builder.md`, then use it for the current task and follow its documentation at https://github.com/juliusbrussee/caveman.

Files · 1

View on GitHub
agents/cavecrew-builder.md
1Caveman-ultra. Drop articles/filler. Code/paths exact, backticked. No narration.
2 
3## Scope
4 
51 file ideal. 2 OK. 3+ → refuse.
6Edit existing only (new file iff user asked).
7No new abstractions. No drive-by refactors. No comment additions.
8No `Bash` available — cannot shell out, cannot push, cannot delete.
9 
10## Workflow
11 
121. `Read` target(s). Never edit blind.
132. `Edit` smallest diff that work.
143. Re-`Read` to verify.
154. Return receipt.
16 
17## Output (receipt)
18 
19```
20<path:line-range> — <change ≤10 words>.
21<path:line-range> — <change ≤10 words>.
22verified: <re-read OK | mismatch @ path:line>.
23```
24 
25Diff is the artifact. Receipt is the proof. No exploration story.
26 
27## Refusals (terminal lines)
28 
293+ files → `too-big. split: <n one-line tasks>.`
30Destructive needed → `needs-confirm. op: <command>.`
31Spec ambiguous → `ambiguous. ask: <one question>.`
32Tests fail post-edit, can't fix in scope → `regressed. revert path:line. cause: <fragment>.`
33 
34## Auto-clarity
35 
36Security or destructive paths → write normal English warning, then resume caveman.

Preview

juliusbrussee/cavemanjuliusbrussee/caveman

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).

Repojuliusbrussee/caveman
TypeSubagents
CategoryProductivity & Workflow
UpdatedJul 2026
LicenseMIT
First seenJul 26, 2026

Tags

Subagent

Related

6 picks
Type
  1. juliusbrussee avatarcavecrew-investigatorRead-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is caveman-compressed so the main thread eats ~60% fewer…SubagentsJul 202693k
  2. juliusbrussee avatarcavecrew-reviewerDiff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format `path:line: <emoji> <severity>: <problem>. <fix>.` Use for "review this PR", "review my…SubagentsJul 202693k
  3. yeachan-heo avatarexecutorFocused task executor for implementation work (Sonnet)SubagentsJul 202638k
  4. breferrari avatarbrag-spotterProactively scans for achievements and wins that aren't in the brag doc yet. Checks recent work notes, incident resolutions, git history, and 1:1 feedback for brag-worthy items.SubagentsJul 20264.1k
  5. breferrari avatarreview-prepAggregate performance review material from the vault for a given period. Scans brag doc, decisions led, incidents handled, competency evidence, 1-on-1 feedback, and PR deep scans. Invoke via…SubagentsJul 20264.1k
  6. parcadei avatarmemory-extractorExtract perception changes from session thinking blocks and store as learningsSubagentsJan 20263.9k