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 developgit 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/develop)<a href="https://agentmods.dev/skills/haposoft/cafekit/develop"><img src="https://agentmods.dev/badge/skills/haposoft/cafekit/develop/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/develop"><img src="https://agentmods.dev/badge/skills/haposoft/cafekit/develop.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 | $0.00027 | $0.02364 |
| Opus 5.5 | $0.00011 | $0.00946 |
| Sonnet 5.5 | $0.00005 | $0.00473 |
| Haiku 4.5 | $0.00003 | $0.00236 |
Grade A, and why
cf:develop 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 today.
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 ships with it
4 files 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.
- today Changed 26e1c0bfbf6e
- yesterday Changed · -55 lines · -7 tokens per session 93296ec048aa
- 1mo ago Changed · -1 tokens per session 9f344e39c3d0
- 1mo ago First seen · 179 lines · 35 tokens per session scan A 0358364a7582
cf:develop is a skill published in the GitHub repository haposoft/cafekit (54 stars, last pushed yesterday), with no licence file. It adds 27 tokens to every session and 2,364 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
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
ai-loop
Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.
triton-cuda-debugging
A troubleshooting checklist for Triton CUDA kernels, covering compilation failures, runtime errors, incorrect results, and performance problems. It includes checks for memory bounds, indexing, shapes, concurrency, and launch settings.
fable-operator
Use when a substantive request needs verified, calibrated reasoning — analysis, diagnosis, review, advice, or a draft the user will act on — even when rigor is not asked for, and most of all when being wrong is expensive or irreversible. NOT casual chat (rigor theater), NOT the SDD gates verify, debug, review; this is…
error-handling
A guide to detecting and reporting errors in GPU code, especially CUDA programs. It covers checks during compilation-related setup, kernel launch, and execution.
rtl-bug-repro
Reproduce an RTL bug with a minimal TB and isolate root cause via waveform diff — 'reproduce this bug', 'minimal repro TB', regression failure isolation.