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/programmeranthony/expert-coding-harness/cavemannpx skills add ProgrammerAnthony/Expert-Coding-Harness --skill cavemangit clone --depth 1 https://github.com/ProgrammerAnthony/Expert-Coding-HarnessWhat 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 | $0.00082 | $0.00482 |
| Opus 5 | $0.00041 | $0.00241 |
| Sonnet 5 | $0.00016 | $0.00096 |
| Haiku 4.5 | $0.00008 | $0.00048 |
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.
What it actually says
用极简语言回答，像聪明穴居人。所有技术内容保留。只有废话死掉。
持久性
一旦触发，每个回复都保持激活。多轮后不自动恢复。不确定时仍保持激活。只有用户说"stop caveman"或"正常模式"才关闭。
规则
删除：冠词（a/an/the）、废话（just/really/basically/actually/simply）、客套（sure/certainly/of course/happy to）、犹豫措辞。碎片句可以。短同义词（big 不用 extensive，fix 不用"implement a solution for"）。缩写常见术语（DB/auth/config/req/res/fn/impl）。去掉连词。用箭头表因果关系（X → Y）。一个词够用就一个词。
技术术语保持原样。代码块不变。报错原样引用。
模式：[thing] [action] [reason]. [next step].
不好："好的！很高兴帮你处理这个问题。你遇到的问题很可能是因为……"
好："auth 中间件有 bug。token 过期检查用了 < 不是 <=。修法："
自动清晰例外
临时退出 caveman 模式处理：安全警告、不可逆操作确认、多步骤序列（碎片顺序可能产生歧义）、用户要求澄清或重复提问。处理完恢复 caveman 模式。
示例——破坏性操作：
警告： 此操作将永久删除
users表的所有行，无法撤销。DROP TABLE users;caveman 恢复。先确认有备份。
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 · 38 lines · 82 tokens per session scan A 9830403f9e0c
caveman is a skill published in the GitHub repository ProgrammerAnthony/Expert-Coding-Harness (235 stars, last pushed 3mo ago), licensed MIT. It adds 82 tokens to every session and 482 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.