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/shikokuchuo/secretbase/agents-mdgit clone --depth 1 https://github.com/shikokuchuo/secretbaseWrote 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/shikokuchuo/secretbase/agents-md)<a href="https://agentmods.dev/instructions/shikokuchuo/secretbase/agents-md"><img src="https://agentmods.dev/badge/instructions/shikokuchuo/secretbase/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 | $0.00951 | $0.00951 |
| Opus 5 | $0.00476 | $0.00476 |
| Sonnet 5 | $0.00190 | $0.00190 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
secretbase 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 3d 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
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 3d ago First seen · 64 lines · 951 tokens per session scan A 1c2b2cf1bcde
secretbase AGENTS.md is an instructions file published in the GitHub repository shikokuchuo/secretbase (19 stars, last pushed 28d ago), with no licence file. It adds 951 tokens to every session, about $0.0048 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 2026-09-01.
Other instructions, from other repositories
duckdb-r AGENTS.md
AGENTS.md instructions for duckdb/duckdb-r, covering working on duckdb-r, the first five minutes and everything else.
huxtable AGENTS.md
AGENTS.md instructions for hughjonesd/huxtable, covering instructions to llm agents, documentation, writing code, tests and docs, testing your work and installing extra components.
MCPR CLAUDE.md
Claude Code instructions for phisanti/MCPR, covering agent instructions, executive summary, the mcpr vision, codebase at a glance and r library contexts.
mcptools CLAUDE.md
Claude Code instructions for posit-dev/mcptools, a project described as: Model Context Protocol For R.
mcptools AGENTS.md
AGENTS.md instructions for posit-dev/mcptools, a project described as: Model Context Protocol For R.
MCPR AGENTS.md
AGENTS.md instructions for phisanti/MCPR, a project described as: MCPR enables AI agents to participate in interactive R sessions for professional analysis workflows.