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 instructions/ja11sop/cuppa/agents-mdgit clone --depth 1 https://github.com/ja11sop/cuppaWrote 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/instructions/ja11sop/cuppa/agents-md)<a href="https://agentmods.dev/instructions/ja11sop/cuppa/agents-md"><img src="https://agentmods.dev/badge/instructions/ja11sop/cuppa/agents-md.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 | $0.13327 | $0.13327 |
| Opus 5 | $0.06663 | $0.06663 |
| Sonnet 5 | $0.02665 | $0.02665 |
| Haiku 4.5 | $0.01333 | $0.01333 |
Grade A, and why
Cuppa build system scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
anonymous reads use the public GitHub HTTP API, `curl`, or `urllib` — still not `gh`. The source is not reproduced here
Licensed BSL-1.0
The repository is licensed BSL-1.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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 · +37 lines · +935 tokens per session ba738a349c8b
- 4d ago First seen · 898 lines · 12,392 tokens per session scan A 7880eb011f25
Cuppa build system is an instructions file published in the GitHub repository ja11sop/cuppa (23 stars, last pushed today), licensed BSL-1.0. It adds 13,327 tokens to every session, about $0.0666 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
xiaozhi-esp32 AGENTS.md
AGENTS.md instructions for 78/xiaozhi-esp32, covering agents.md, project, architecture, required rules and boards and configuration.
compiler-explorer AGENTS.md
AGENTS.md instructions for compiler-explorer/compiler-explorer, covering agents.md, build & test commands, important workflow requirements, style guidelines and architecture guidelines.
moon AGENTS.md
AGENTS.md instructions for moonrepo/moon, covering agents.md, repository layout, prerequisites, rust workflow and conventions.
rocketride-server AGENTS.md
AGENTS.md instructions for rocketride-org/rocketride-server, covering agents.md and co-located documentation rule.
monkey AGENTS.md
Instructions for monkey/monkey, covering agents, repository map, main runtime flow, build and verification and commit style used in this repository.
flamerobin copilot-instructions.md
Copilot instructions for mariuz/flamerobin, covering flamerobin — copilot instructions, build, run from build dir (sets up paths to resource subdirs), tests and or with verbose boost.test output.