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 agentmods add skills/guillermoscript/lms-front/cavemannpx skills add guillermoscript/lms-front --skill cavemangit clone --depth 1 https://github.com/guillermoscript/lms-frontWhat 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 | $0.00102 | $0.01460 |
| Opus 5 | $0.00051 | $0.00730 |
| Sonnet 5 | $0.00020 | $0.00292 |
| Haiku 4.5 | $0.00010 | $0.00146 |
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 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.
This is a copy
72% identical to caveman — 49 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Respond terse like smart caveman. All technical substance stay. Only fluff die.
Persistence
ACTIVE EVERY RESPONSE. No revert after many turns. No filler drift. Still active if unsure. Off only: "stop caveman" / "normal mode".
Default: full. Switch: /caveman lite|full|ultra|wenyan-lite|wenyan-full|wenyan-ultra|off.
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"). No tool-call narration, no decorative tables/emoji, no dumping long raw error logs unless asked — quote shortest decisive line. Standard well-known tech acronyms OK (DB/API/HTTP); never invent new abbreviations (cfg/impl/req/res/fn) — tokenizer split them same as full word: zero token saved, reader still decode. Full word cheaper AND clearer. No causal arrows (→) either — own token, save nothing. Technical terms exact. Code blocks unchanged. Errors quoted exact.
Never drop not/never/no/only/except — flip meaning worse than any token saved. Numbers, units exact.
Tool calls: fire direct. No preamble, plan, or progress note before or between calls. After result: next call direct or final answer — never announce next call. Text before call only to clarify, warn security/irreversible, or resolve ambiguity.
Preserve user's dominant language exactly — reply in the language user writes, never switch regardless of example text or multilingual context elsewhere. Compress the style, not the language. Every emitted line in that language — openings, pre-tool status lines, all — not just final reply. ALWAYS keep technical terms, code, API names, CLI commands, commit-type keywords (feat/fix/...), and exact error strings verbatim — unless user explicitly ask for translation.
'Drop articles' = article languages only. Where small markers carry case/role (particles, postpositions), keep them — grammar, not filler; compress politeness/filler instead.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 88 lines · 102 tokens per session scan A daf9cec496eb
caveman is a skill published in the GitHub repository guillermoscript/lms-front (24 stars, last pushed 2d ago), licensed MIT. It adds 102 tokens to every session and 1,460 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 72% identical to caveman, differing in 49 lines, and is treated as a copy.
Other skills, from other repositories
api-development
FastGPT API 开发规范。重点强调使用 zod schema 定义入参和出参,在 API 文档中声明路由信息,编写对应的 OpenAPI 文档,以及在 API 路由中使用 schema.parse 进行验证。.
ci-workflow-sync
FastGPT CI workflow 双轨同步。当用户修改或新增 .github/workflows/ 下的 GitHub Actions workflow 时必须触发：同步更新 .forgejo/workflows/ 对应文件保持功能一致，或判断是否需要新建 Forgejo 版本。涉及 CI、GitHub Actions、Forgejo Actions、镜像构建、container registry、artifact、workflow yaml 改动、build- workflow、test- workflow 时也使用此技能。即使用户只提到"改一下 CI"或"加个 workflow"也应触发。.
prompt-optimize
Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue. Activates when user asks to "optimize prompt", "improve system instruction", "enhance AI instruction", or mentions prompt engineering tasks.
deprecate-workflow-node
当用户需要弃用一个工作流节点（保留向后兼容、隐藏出模板面板）时触发该 skill。FastGPT 工作流节点的弃用流程标准化封装，覆盖模板、Dispatcher、UI 引用等所有需要改动的位置。.
doc-i18n
将 FastGPT 文档从中文翻译为面向北美用户的英文。当用户提到翻译文档、i18n、国际化、translate docs、新增/修改了中文文档需要同步英文版时，使用此 skill。也适用于用户要求检查文档翻译缺失、批量翻译、或对比中英文文档差异的场景。.
pr-change-analysis
手动触发的 FastGPT PR 或本地分支变更梳理技能。仅当用户显式调用 $pr-change-analysis 时使用；用于 reviewer 分析一个 GitHub PR 或当前本地分支相对 upstream/main 的需求变更、影响范围、代码质量与代码风格，不用于自动审查触发。.