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 Mte90/dotfiles --skill cavemangit clone --depth 1 https://github.com/Mte90/dotfilesWrote 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/mte90/dotfiles/caveman)<a href="https://agentmods.dev/skills/mte90/dotfiles/caveman"><img src="https://agentmods.dev/badge/skills/mte90/dotfiles/caveman/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/mte90/dotfiles/caveman"><img src="https://agentmods.dev/badge/skills/mte90/dotfiles/caveman.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00073 | $0.00552 |
| Opus 5.5 | $0.00029 | $0.00221 |
| Sonnet 5.5 | $0.00015 | $0.00110 |
| Haiku 4.5 | $0.00007 | $0.00055 |
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 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.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 73 lines · 73 tokens per session scan A fb56c999d5a0
caveman is a skill published in the GitHub repository Mte90/dotfiles (51 stars, last pushed 7d ago), with no licence file. It adds 73 tokens to every session and 552 once invoked, about $0.0003 per session on Opus 5.5. 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
herdr
Use when the user mentions herdr or is working inside a herdr pane and wants to save/restore a pane layout, change herdr's theme, prefix or other preferences on this host only, start or check on an agent in another herdr pane, add, turn off or open a herdr plugin (file viewer, keybindings), or asks why the herdr…
create-handoff
Save the session's durable half as a memory file (save-memory), then write the perishable half -- the handoff prompt for the next session -- to a well-known place in the /.ai-memory repository and push it, so the next session, local or in the cloud, can pick the work up with read-handoff or pop-handoff and nobody has…
sync-global-kiro-skils
Reconcile the live global Kiro permissions under /.kiro/settings with their version-controlled template under /.dotfiles/.kiroglobal/settings, while verifying the global skills and steering links. Use when the user asks to sync, mirror, or reconcile global Kiro settings with dotfiles, or invokes…
resume-from-chat-history
A recovery workflow for continuing a Kiro coding chat after it breaks or is lost by reading the saved session files on disk.
toil-offloading-pi
Orchestrate decomposable workloads with pi subagents (afang-subagent extension): the strong-but-slow root agent clarifies goals, cuts the work into contract-bearing subtasks, fans them out to cheap-and-fast subagents, grades delivery risk, runs an independent review where it pays, and accepts the result. Use when the…
save-pipeline-memory
Capture a multi-step workflow into a timestamped pipeline memory after trial-and-error sessions. The core output is: (1) the final working commands saved as executable scripts (not bare shell commands), and (2) a structured markdown document separating the clean reproducible pipeline from the detours and pitfalls.…