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/eigenwise/eigenwise-toolshed/claude-mdgit clone --depth 1 https://github.com/Eigenwise/eigenwise-toolshedWrote 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/eigenwise/eigenwise-toolshed/claude-md)<a href="https://agentmods.dev/instructions/eigenwise/eigenwise-toolshed/claude-md"><img src="https://agentmods.dev/badge/instructions/eigenwise/eigenwise-toolshed/claude-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 | $0.00615 | $0.00615 |
| Opus 5 | $0.00308 | $0.00308 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
eigenwise-toolshed CLAUDE.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 4d 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 — 22 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eigenwise Toolshed — project rules
Documentation stays current, and an agent owns that
Most of what this repo ships is read by agents, not by people. An orchestrator or executor mid-run never opens the docs site; it learns what is true from tool schemas, refusal messages, briefings, skill text, and live-rules. So a change has two audiences, and they are not equally expensive to get wrong.
-
Agent-facing surfaces (MCP tool schemas and descriptions, refusal and guidance strings, briefing text, agent/skill definitions, CLI help, live-rules): these are the contract. An agent acts on them immediately, so drift here costs a dispatch every time it is hit. Update them IN the same change, never as a follow-up ticket. If a behavior changed and the string that tells an agent about it did not, the change is not done. When a value is enumerated in code, that enum is the source of truth and every surface repeating it must be checked against it.
-
Generated pages (
docs/src/content/docs/reference/): built bydocs/scripts/generate-reference.mjsfrom plugin manifests, SKILL.md frontmatter, hooks.json, and the marketplace file. NEVER hand-edit these — they regenerate on every docs deploy, and the deploy workflow triggers on plugin manifest/skill/hook changes, so they cannot drift. If a generated page is wrong, fix the generator or the source manifest. -
Prose pages (getting started, setup guides, observability, architecture): written for a human reading about the system, not for an agent operating it. These are maintained BY THE AI AGENT working the change: any ticket that alters observable behavior — a new or renamed skill, a changed setup flow, new config, a new dashboard section, changed CLI surface — updates the affected page(s) under
docs/src/content/docs/in the same story, or files a linkeddocs-writingticket on the board before the ship closes. A behavior change whose docs ticket doesn't exist is not done. Stale prose is a correctness bug, but it is not an outage; do not let it outrank a drifting agent-facing surface.
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.
- 4d ago First seen · 22 lines · 615 tokens per session scan A 9bd0684c16a9
eigenwise-toolshed CLAUDE.md is an instructions file published in the GitHub repository Eigenwise/eigenwise-toolshed (36 stars, last pushed 6d ago), licensed MIT. It adds 615 tokens to every session, about $0.0031 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.