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 haposoft/cafekit --skill researchgit clone --depth 1 https://github.com/haposoft/cafekitWrote 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/haposoft/cafekit/research)<a href="https://agentmods.dev/skills/haposoft/cafekit/research"><img src="https://agentmods.dev/badge/skills/haposoft/cafekit/research/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/haposoft/cafekit/research"><img src="https://agentmods.dev/badge/skills/haposoft/cafekit/research.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 | $0.00023 | $0.00906 |
| Opus 5.5 | $0.00009 | $0.00362 |
| Sonnet 5.5 | $0.00005 | $0.00181 |
| Haiku 4.5 | $0.00002 | $0.00091 |
Grade A, and why
cf:research 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 yesterday.
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.
- yesterday Changed · -29 lines 938dd94fcc96
- 1mo ago Changed · +27 lines · -12 tokens per session 1c3d14dffded
- 1mo ago First seen · 59 lines · 35 tokens per session scan A 008b208e1ecd
cf:research is a skill published in the GitHub repository haposoft/cafekit (54 stars, last pushed yesterday), with no licence file. It adds 23 tokens to every session and 906 once invoked, about $0.0001 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
terminal-diagrams
Reference for drawing any diagram as plain monospace terminal text — box-drawing/ASCII, no external renderer. Read when work-preferences.md's trigger fires.
codebase-gap-analysis
Analyze a user's codebase against a reference architecture to identify gaps and provide prioritized enhancement recommendations.
ai-agent-evaluation-benchmarking
Autonomous AI agent benchmark evaluation register: task completion rates, planning accuracy, tool invocation precision, and cost benchmarks.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
backend
Everything on the Node side of a LangWatch module: composing a process (apps/api, apps/worker, apps/tasks), Server/container/boot, a module's process-half shape, the four-way rule for what a module may demand, declaring REST endpoints and tRPC procedures, the worker role (drain order, eventing pipelines, process…