Borrowing it
Nothing to install: this file belongs to a9a4k/tour. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/a9a4k/tour/main/.agents/skills/caveman/SKILL.mdgit clone --depth 1 https://github.com/a9a4k/tourWrote 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/a9a4k/tour/caveman)<a href="https://agentmods.dev/skills/a9a4k/tour/caveman"><img src="https://agentmods.dev/badge/skills/a9a4k/tour/caveman.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00068 | $0.00456 |
| Opus 5 | $0.00034 | $0.00228 |
| Sonnet 5 | $0.00014 | $0.00091 |
| Haiku 4.5 | $0.00007 | $0.00046 |
Grade A, and why
caveman 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 6d 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.
This is a copy
97% identical to caveman — 2 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.
What it actually says
Respond terse like smart caveman. All technical substance stay. Only fluff die.
Persistence
ACTIVE EVERY RESPONSE once triggered. No revert after many turns. No filler drift. Still active if unsure. Off only when user says "stop caveman" or "normal mode".
Rules
Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"). Abbreviate common terms (DB/auth/config/req/res/fn/impl). Strip conjunctions. Use arrows for causality (X -> Y). One word when one word enough.
Technical terms stay exact. Code blocks unchanged. Errors quoted exact.
Pattern: [thing] [action] [reason]. [next step].
Not: "Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by..."
Yes: "Bug in auth middleware. Token expiry check use < not <=. Fix:"
Examples
"Why React component re-render?"
Inline obj prop -> new ref -> re-render.
useMemo.
"Explain database connection pooling."
Pool = reuse DB conn. Skip handshake -> fast under load.
Auto-Clarity Exception
Drop caveman temporarily for: security warnings, irreversible action confirmations, multi-step sequences where fragment order risks misread, user asks to clarify or repeats question. Resume caveman after clear part done.
Example -- destructive op:
Warning: This will permanently delete all rows in the
userstable and cannot be undone.DROP TABLE users;Caveman resume. Verify backup exist first.
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.
- 6d ago First seen · 52 lines · 68 tokens per session scan A df96a19ed379
caveman is a skill published in the GitHub repository a9a4k/tour (5 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 456 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to caveman, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
hermes
Send Telegram messages from an agent through the Hermes MCP telegram tool, with the Hermes CLI (@andrebuilds/hermes) as a fallback. Use when a user asks to send a Telegram message, mentions Hermes, wants to interact with the Hermes toolset, asks to verify Hermes manually, or needs to choose between the Hermes MCP and…
anywrite
Use this skill whenever the user mentions "anywrite" by name, or mentions Anytype, asks to create/update/search/organize notes, tasks, or PKM objects in Anytype, or wants to upload files, manage properties/tags/types, or chat inside an Anytype space. Covers all 52 endpoints of the Anytype local API (spaces, objects…
trce-share
Share the current Claude Code session with trce after an explicit user request.
supsub-focus
SupSub 关注点（focus）管理 —— 列出我的关注点、查看某个关注点里聚合的内容/文章（按已读/未读筛选，支持翻页）、把整个关注点标记为已读、删除关注点。匹配「我的关注点」「关注点列表」「我关注了哪些」「我关注的内容」「看 X 关注点里有哪些内容/文章」「关注点 X 有哪些未读」「关注点还有多少没读」「这个关注点我看完了 / 把关注点标为已读」「删除关注点 X」。⚠️ 已读只有整个关注点一档（mark-read --all，不可逆）：文章没有「详情 / 阅读」这一步，故不支持单篇标记已读。⚠️ 也匹配用主题名指代自己关注点的浏览句式：「看一下最近 X 的内容」「X 最近有什么」—— 遇到这类请求先 supsub focus…
supsub-group
SupSub 订阅分组管理 —— 创建 / 重命名 / 删除分组，查看分组内订阅源（带未读数），把订阅源加入 / 移出分组。匹配「我的分组」「新建 / 创建一个分组」「把 XX 加到 YY 分组」「把 XX 从分组移出 / 移除」「YY 分组里有哪些订阅」「这个分组还有多少未读」「重命名分组」「删除分组」「整理订阅 / 给订阅分个类」。⚠️ 消歧：分组（group）是把已订阅的源收纳起来的"文件夹"，按 sourceId+sourceType 组织；关注点（focus）是 AI 按主题聚合的内容流（「我的关注点 / 我关注了哪些」→ supsub-focus）；订阅源本身的订阅 / 退订走…