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/genged/capshelf/agents-mdgit clone --depth 1 https://github.com/genged/capshelfWhat 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 | $0.02491 | $0.02491 |
| Opus 5 | $0.01246 | $0.01246 |
| Sonnet 5 | $0.00498 | $0.00498 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade A, and why
capshelf 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file gives coding agents the shared project context that should be true for every task in this repository. Keep it concise; prefer pointers to the living docs and source over copying long procedures here.
Writing Style
- Write technical text with the rules of ASD-STE100 Simplified Technical English. STE is the controlled language that aerospace and defense manufacturers use for maintenance documentation. The rules exist so that a tired reader who is not a native English speaker cannot misread an instruction. They remove the usual signs of AI-generated text as a side effect: long sentences, synonym rotation, hedges, filler, and decorative clauses.
- Write for that tired reader. Each sentence must survive one read.
- Technical prose only, be direct
- When the user asks a question, answer it first before making edits or running implementation commands.
- These rules cover every document you write or edit. They are not only for
conversation. They apply to
docs/,README.md, release notes, commit messages, and this file. - This file beats the prose of an older document. Many pages under
docs/predate these rules. If a task tells you to follow an existing page, copy its structure and its section order. Do not copy its prose habits. - In release notes and What's New pages, use the simple past for a change that
the release made: "Added
--merge". Use the simple present for behavior that the software now has: "A conflict writes nothing." Do not use the imperative for a change. It reads as an instruction to the reader. - Before you commit a document, check the prose mechanically: count the words
in each sentence outside a code fence, and grep for
—,;, and hedge words.
Project
capshelf is a Bun/TypeScript CLI for managing shared Coding Agent
configuration across projects. It materializes user-owned skills, settings
fragments, and future MCP config from a Git-backed data repo into consuming
projects.
More info: docs/project-brief.md, docs/architecture.md, docs/cli.md,
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 · 188 lines · 2,491 tokens per session scan A 1d7a09a0e7d9
capshelf AGENTS.md is an instructions file published in the GitHub repository genged/capshelf (10 stars, last pushed 8d ago), licensed MIT. It adds 2,491 tokens to every session, about $0.0125 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 2026-08-31.
Other instructions, from other repositories
cortex-mem AGENTS.md
Instructions for sopaco/cortex-mem, covering cortex memory - ai agent context guide, project overview, core concepts, memory dimensions and three-tier layers.
ai-toolkit AGENTS.md
Instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
superpowers-reasonix AGENTS.md
Instructions for christopherarter/superpowers-reasonix, covering project guidance, skills — stop. load a skill before you act, red flags — these thoughts mean stop. you are rationalizing and priority.
ai-mind AGENTS.md
Instructions for HWYD/ai-mind, covering agents, version spec workspace continuity (mandatory), 项目定位, 事实来源优先级 and 开始大改前先读什么.
agent-skills AGENTS.md
Instructions for sayeed1999/agent-skills, covering agents.md, output style, output style, 1. think before code and 2. simplicity.
webflow-skills AGENTS.md
Instructions for 224-Industries/webflow-skills, covering 224 industries - webflow agent skills repository, agents.md (symlink to claude.md), repo structure, reference file conventions and content style.