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/stepfunctionllc/mcp-server-cantera/claude-mdgit clone --depth 1 https://github.com/StepFunctionLLC/mcp-server-canteraWhat 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 | $0.00719 | $0.00719 |
| Opus 5 | $0.00360 | $0.00360 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
mcp-server-cantera 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 yesterday.
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.
This is a copy
100% identical to mcp-server-cantera AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation contract for coding agents
This repository's public documentation is generated automatically by the Step Function
documentation agent (Documentation-Agent),
which reads this repo and maintains a page on the centralized Sphinx + MyST site
(https://coot.tail28751.ts.net/). It builds the page in this structure:
Overview (intent) · Background & Theory · Architecture (with a diagram) · Usage · API Reference (concise) · Configuration · Notes
The docs are professional engineering documentation: they lead with the theory, the architecture, and the design logic — the API listing is a brief orientation, not the substance. The agent is accurate-by-design: it documents only what this repo actually states, and it will not invent the intent or the theory. So when you change code here, keep the source material below current — otherwise the generated docs go stale or omit context.
What to maintain (so the docs are good)
- Intent — in the README's opening / Overview. One short statement of what this repo is and the problem it solves. Update it when the purpose shifts.
- Background & Theory — write it down; it cannot be derived from code. Keep a section
(in the README, or a
THEORY.md/DESIGN.md) describing the scientific / mathematical / engineering basis: the methods, models, governing equations, assumptions, and approach the code implements, with references/citations where relevant. This is the highest-leverage thing to maintain — if it isn't written here, it won't appear in the docs. Update it whenever you change the method, not just the code. - Architecture & design rationale — write down the why. In the README or a
DESIGN.md/ARCHITECTURE.md, describe the major components and their responsibilities, how data/control flows between them, and the key design decisions and trade-offs. The agent draws the architecture diagram and the supporting-logic discussion from the code and this prose — explaining intent and trade-offs that code alone can't convey makes the docs far stronger. - API details — in accurate docstrings. Public functions, classes, and commands should have docstrings with correct signatures, parameters, returns, and units. The agent distills these into a concise API Reference (key entry points only); private/internal names (leading underscore, tests, build glue) are intentionally left out.
- Usage — minimal, runnable examples in the README (install + the primary workflow). Keep them working.
- Configuration — document environment variables, CLI flags, and config files.
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.
- yesterday First seen · 49 lines · 719 tokens per session scan A 940c66cdbad5
mcp-server-cantera CLAUDE.md is an instructions file published in the GitHub repository StepFunctionLLC/mcp-server-cantera (4 stars, last pushed 2d ago), licensed MIT. It adds 719 tokens to every session, about $0.0036 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to mcp-server-cantera AGENTS.md, differing in 0 lines, and is treated as a copy.
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.