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/johnthreekay/ryokan/agents-mdgit clone --depth 1 https://github.com/johnthreekay/RyokanWhat 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 | $0.15162 | $0.15162 |
| Opus 5 | $0.07581 | $0.07581 |
| Sonnet 5 | $0.03032 | $0.03032 |
| Haiku 4.5 | $0.01516 | $0.01516 |
Grade B, and why
Ryokan AGENTS.md scanned grade B 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 2d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **`mold` + `clang`** — `.cargo/config.toml` pins `linker = "clang"` with `-fuse-ld=mold` for x86_64 + aarch64 Linux. Cuts incremental link time 3-5× vs ld/lld; without them a build fails with `"linker 'clang' not found 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.
- 2d ago First seen · 248 lines · 15,162 tokens per session scan B 5d80e94d6d8e
Ryokan AGENTS.md is an instructions file published in the GitHub repository johnthreekay/Ryokan (5 stars, last pushed 3d ago), licensed GPL-3.0. It adds 15,162 tokens to every session, about $0.0758 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
kari AGENTS.md
Instructions for Dhairya3391/kari, covering ai agent guidelines, 1. core mandates, 2. refactor logic (the "must needed" flexibility), 3. communication patterns and 4. error handling.
anilist-mcp-server AGENTS.md
AGENTS.md instructions for Grinv/anilist-mcp-server, covering agents.md, project shape, why this server exists, commands and conventions.
anime-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/anime-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
anime-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/anime-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
anilist-mcp-server CLAUDE.md
Claude Code instructions for Grinv/anilist-mcp-server, a project described as: MCP server for the AniList GraphQL API — anime/manga search, details, and personal list management.
AniShelf AGENTS.md
Instructions for samuelhe52/AniShelf, covering anishelf - developer notes, workflow, code style, testing and commits.