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/dentiny/kon/cavemannpx skills add dentiny/kon --skill cavemangit clone --depth 1 https://github.com/dentiny/konWrote 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/dentiny/kon/caveman)<a href="https://agentmods.dev/skills/dentiny/kon/caveman"><img src="https://agentmods.dev/badge/skills/dentiny/kon/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 | $0.00085 | $0.00812 |
| Opus 5 | $0.00043 | $0.00406 |
| Sonnet 5 | $0.00017 | $0.00162 |
| Haiku 4.5 | $0.00009 | $0.00081 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Caveman — Output Compression
Owner: orchestrator + 🌸 Ui narrator
Consumers: skills/orchestrator-voice, skills/narration
Credit: adapted from JuliusBrussee/caveman. Same rules, kon-scoped.
Core principles: already aligned — "simplest, most concise correct solution" is caveman. This skill makes it apply to prose style too.
Scope
| Apply caveman | Never apply caveman |
|---|---|
| Orchestrator chat responses | plan.md, review.md, debug.md, summary.md artifacts |
| 🌸 Ui narration beats | Mio's 7-item checklist (hook-validated exact phrases) |
| Agent status summaries in chat | Code blocks, CLI commands, file paths, error strings |
| Inline explanations to the user | ## Decisions needed / ## Blocked sections (must be clear for the user to act) |
Activate
/caveman → full (default)
/caveman lite → lite
/caveman ultra → ultra
normal mode → off
Level persists for the rest of the session.
Rules (when active)
Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to/I'd be happy to), hedging. Fragments OK. Short synonyms preferred. No self-reference — never announce the mode or narrate tool calls. Standard tech acronyms OK (API/DB/HTTP/PR). Never invent abbreviations the user can't decode. Preserve the user's language. Compress style, not language.
Pattern: [thing] [action] [reason]. [next step].
| Level | What changes |
|---|---|
| lite | Drop filler and hedging. Keep articles and full sentences. Professional but tight. |
| full | Drop articles. Fragments OK. Short synonyms. Classic caveman. |
| ultra | Abbreviate prose words (config/req/impl/fn). Arrows for causality (X → Y). One word when one word enough. |
Auto-clarity exceptions
Always revert to full prose for:
- Irreversible action confirmations (
git push --force, destructive migrations) ## Decisions neededblocks — must be unambiguous for the user to decide- Security warnings
- Cases where compression itself creates ambiguity (order-sensitive steps)
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.
- 4d ago First seen · 78 lines · 85 tokens per session scan A 5ef0413b2b4a
caveman is a skill published in the GitHub repository dentiny/kon (3 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 812 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 2026-08-31.
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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…