curie: Instructions file for Claude Code

CLAUDE.md

curie CLAUDE.md is an instructions file for Claude Code from curie-eng/curie. It costs 1,106 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for the curie command-line tool, including release selection and architecture decision records. A command-line tool is a program operated by typing commands in a terminal.

In plain words
What is it for?
Use them when building, installing, updating, or operating curie, and when documenting architecture decisions or release workflows.
Why use it?
They keep development and operational tasks behind one discoverable curie interface instead of scattering setup steps across scripts and raw commands.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions AGENTS.md.

This is curie-eng/curie's own configuration. It tells Claude Code how to work on curie itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything curie configures →

Reuse

Borrowing it

Nothing to install: this file belongs to curie-eng/curie. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/curie-eng/curie/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/curie-eng/curie

Made for: Claude Code.

Wrote 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.

agentmods badge for curie CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/curie-eng/curie/claude-md/github.svg)](https://agentmods.dev/instructions/curie-eng/curie/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/curie-eng/curie/claude-md"><img src="https://agentmods.dev/badge/instructions/curie-eng/curie/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for curie CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/curie-eng/curie/claude-md"><img src="https://agentmods.dev/badge/instructions/curie-eng/curie/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,106 This file is loaded in full into every session.
When invoked 1,106 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01106 $0.01106
Opus 5 $0.00553 $0.00553
Sonnet 5 $0.00221 $0.00221
Haiku 4.5 $0.00111 $0.00111

Measured 10d ago against content hash b7f1d6de918c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

curie 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 10d 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.

CLAUDE.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

See AGENTS.md - the agent instructions for this repo live there.

One entry point: curie <command>

Dev and operator flows go through the curie CLI, not loose shell scripts or bare tool invocations. When you would otherwise add a ./scripts/foo.sh, tell someone to run a raw docker/helm/uv/pnpm command, or document a multi-step setup, add or extend a curie subcommand instead — a single, discoverable surface beats a scatter of scripts. The script or tool call can stay the implementation; it just isn't the interface.

  • Building the runner image → curie build (not a copy-pasted docker build -f runner/Dockerfile ...). That tags both curie-runner (what curie skill up runs) and ghcr.io/curie-eng/curie-runner:dev (what curie local up --build runs), so curie update --image refreshes a --build stack's runner.
  • First-run dev bootstrap → curie install (or ./get-curie.sh from a source checkout, which also puts curie on PATH the first time by building it).
  • Refresh the on-PATH CLI after a code change → curie update (rebuilds and cargo installs the CLI to ~/.cargo/bin; --image also rebuilds the runner). The per-change loop, so you never re-run the bootstrap script.
  • Run the local stack on YOUR checkout → curie local up --build. curie update covers the CLI and the runner image; the stack's api, worker, dispatcher and ui otherwise come from the registry, so a source-built CLI ends up talking to whatever was last published. That skew does not announce itself — it surfaces as a serde error about a field name, or a missing Python module from inside a container (#1915). It needs a source-built curie or an explicit -f compose.dev.yaml: a released binary runs the version-pinned release compose, which cannot read the tags --build writes, so that combination is refused (#1926).
  • Contributor/CI scripts (contract codegen, chart render-asserts, the e2e round-trip) → curie dev <...>. The dev namespace fences off commands that need a source checkout + dev toolchains; they error clearly when run from a released binary.
  • Operator/product commands stay top-level: init, build, skill, local, cluster.

New tooling ships as a curie subcommand (add the clap surface in cli/src/main.rs, the handler in cli/src/commands.rs); a new loose script in scripts/ should be the exception with a reason, not the default.

Read the full file on GitHub · 60 lines

Changes

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.

  1. 10d ago First seen · 60 lines · 1,106 tokens per session scan A b7f1d6de918c

Subscribe to this mod's changes

curie CLAUDE.md is an instructions file published in the GitHub repository curie-eng/curie (35 stars, last pushed today), licensed Apache-2.0. It adds 1,106 tokens to every session, about $0.0055 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens