caveman is a skill and proxy for coding agents that shortens unnecessary explanatory prose so agents use fewer tokens while leaving code, commands, paths, and error messages unchanged. It is for people using coding agents who want terse responses and lower token use, including with Claude-based workflows. The catalogue entries contain its skills, commands, agents, instructions, and plugins.
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.
npx skills add JuliusBrussee/caveman --skill caveman-discovergit clone --depth 1 https://github.com/JuliusBrussee/cavemanWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/juliusbrussee/caveman/caveman-discover)<a href="https://agentmods.dev/skills/juliusbrussee/caveman/caveman-discover"><img src="https://agentmods.dev/badge/skills/juliusbrussee/caveman/caveman-discover/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/juliusbrussee/caveman/caveman-discover"><img src="https://agentmods.dev/badge/skills/juliusbrussee/caveman/caveman-discover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk pass
- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.01318 |
| Opus 5.5 | $0.00018 | $0.00527 |
| Sonnet 5.5 | $0.00009 | $0.00264 |
| Haiku 4.5 | $0.00004 | $0.00132 |
Grade A, and why
caveman-discover scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
dev script, one curl). Then confirm: the request still succeeds (the gateway Copies of this mod
3 near-identical copies found in the catalogue:
- caveman-discover — 100% identical, 0 lines differ
- caveman-discover — 86% identical, 9 lines differ
- caveman-discover — 86% identical, 9 lines differ
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are labeling this repository's LLM workflows for Caveman Cloud. A
workflow is a job the code performs — "answer a support ticket", "build the
nightly digest", "run the eval suite" — not a technology. Every gateway
request can carry a workflow label; unlabeled traffic all lands in one
unlabeled-workflow bucket. Your job: find the workflows, name them well,
wire the labels, and verify nothing broke.
This changes code, so it goes through the user's normal review: propose the table first, apply after the user agrees. Re-running on an already-labeled repo must change nothing (idempotent).
This skill is operator-invoked. An unlabeled-traffic Cave Plan observation is
review-only and does not create an advisory file, proposal, or Draft PR. Do not
infer that telemetry selected a callsite or authorized an edit. Independently
inventory the repository, present the labeling table, and wait for the user's
approval before changing code.
Step 1 — Inventory the workflows
Walk the repo from its entry points, not from its imports:
- HTTP/RPC handlers that call an LLM (directly or through layers)
- Scheduled jobs: cron definitions, queue consumers, workers, GitHub Actions that invoke LLM code
- CLI commands and scripts (
scripts/,bin/, package.json scripts) - Eval / test harnesses that burn real tokens
- Distinct agents or chains inside a framework (each LangGraph graph, each crew, each agent definition is usually its own workflow)
One workflow = one job a human would name. Ten callsites inside the same
request handler are one workflow; one shared llm.ts helper used by three
jobs is three workflows (label at the callers, never the shared helper).
Step 2 — Name them
Slug grammar (the gateway enforces this): lowercase [a-z0-9_-], 1–96 chars.
Name the job, not the tech:
- Good:
support-reply,nightly-digest,pr-review,eval-suite,onboarding-email - Bad:
openai-calls(tech),main(says nothing),SupportReply(invalid),johns-test-3(won't age)
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.
- 1mo ago First seen · 116 lines · 44 tokens per session scan A 0483d17fce14
caveman-discover is a skill published in the GitHub repository JuliusBrussee/caveman (114,861 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 1,318 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
outlines
Outlines: structured JSON/regex/Pydantic LLM generation.
instructor
Structured LLM outputs validated with Pydantic.
evaluating-llms-harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
weights-and-biases
W&B: log ML experiments, sweeps, model registry, dashboards.
guidance
Constrain LLM output with grammars; guarantee valid JSON.
huggingface-tokenizers
Fast BPE/WordPiece tokenization and custom vocab training.