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/honeymelon-app/honeymelon/agents-mdgit clone --depth 1 https://github.com/honeymelon-app/honeymelonWrote 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/honeymelon-app/honeymelon/agents-md)<a href="https://agentmods.dev/instructions/honeymelon-app/honeymelon/agents-md"><img src="https://agentmods.dev/badge/instructions/honeymelon-app/honeymelon/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 5.1 | $0.00519 | $0.00519 |
| Opus 5 | $0.00260 | $0.00260 |
| Sonnet 5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
honeymelon AGENTS.md 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 6d 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
Licensed GPL-3.0
The repository is licensed GPL-3.0, 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.
- 6d ago First seen · 30 lines · 519 tokens per session scan A cfcc22924aa4
honeymelon AGENTS.md is an instructions file published in the GitHub repository honeymelon-app/honeymelon (26 stars, last pushed 7mo ago), licensed GPL-3.0. It adds 519 tokens to every session, about $0.0026 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 2026-08-30.
Other instructions, from other repositories
video-probe-mcp AGENTS.md
AGENTS.md instructions for dvnc-labs/video-probe-mcp, covering agents.md — build spec for a narrow mcp server artifact, doctrine (non-negotiable), what you edit vs keep, fill src/index.ts and gates (ci runs these).
speech-studio AGENTS.md
Instructions for soniqo/speech-studio, covering agent instructions, project, stack, sibling repos under /repos/ and build.
Premiere-Pro-edit-bibl CLAUDE.md
Instructions for biblcontentofficial-art/Premiere-Pro-edit-bibl, covering premiere pro 자동 편집 프로젝트 and 하네스: 비블 유튜브 영상 편집.
ffmpeg-mcp-lite CLAUDE.md
Instructions for kevinwatt/ffmpeg-mcp-lite, covering claude.md, project overview, technology stack, development commands and install dependencies.
gemini-audio-mcp GEMINI.md
Gemini CLI instructions for jxoesneon/gemini-audio-mcp, covering 🎵 gemini audio mcp - project context, project overview, building and running, prerequisites and commands.
gemini-audio-mcp CLAUDE.md
Claude Code instructions for jxoesneon/gemini-audio-mcp, covering project instructions, tech stack, code style, testing and build & run.