Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →juliusbrussee/cavecrew
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/r
Passed 16 of 21 test cases with the skill, and 5 of 21 without it.
and 13 more in the full report
12 fixed5 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/13/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
You modified `src/auth.py` lines 40-45 but a subsequent re-read check indicates a test broke or validation failed. What single status word is emitted?
| Checked | Without skill | With skill |
|---|---|---|
| Returns status token regressed. when post-edit verification fails | Missed | Passed |
The instructions your model reads when the skill loads.
Cavecrew = three subagent presets that answer in ultracave voice (tool runs: one status line in, one out; nothing between routine calls). 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.
| 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 if installed |
| Review diff, branch, or file for bugs | cavecrew-reviewer |
| Deep code review with rationale + alternatives | Code Reviewer (vanilla) if installed, else main thread |
| 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.
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 comes back as a compressed path:line table instead. Across 20 delegations in one session that's the difference between context exhaustion and finishing the task.
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
test cases passed, vs 5 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.