understudy-agent-tools CLAUDE.md

A set of repository instructions for coding agents working on Understudy, a tool for improving and managing applications that use language models.

In plain words
What is it for?
It is for guiding users of Understudy and contributors working on its code, including setup, behavior, parallel work, and project boundaries.
Why use it?
It tells an agent how to identify its role, follow the project's rules, and choose the right workflow instead of guessing.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/understudylabs/understudy-agent-tools/claude-md
Clone the repo
git clone --depth 1 https://github.com/understudylabs/understudy-agent-tools
Per session 478 This file is loaded in full into every session.
When invoked 478 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00478 $0.00478
Opus 5 $0.00239 $0.00239
Sonnet 5 $0.00096 $0.00096
Haiku 4.5 $0.00048 $0.00048

Measured 2d ago against content hash 08f150c87b46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

understudy-agent-tools 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 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.

CLAUDE.md · 43 lines

What it actually says

CLAUDE.md

Guidance for Claude Code (and any coding agent) working in this repository.

The operating guide for agents is AGENTS.md. Read it first. It covers the two ways an agent is used here and what to do in each.

Prime directive (the 10-second version)

There are two kinds of visitor to this repo. Figure out which one you have before doing anything else:

  • A user who wants to use Understudy — improve an LLM app, cut cost, run a local model, pick a route. Install the plugin first (the install-plugin skill), then run the onboard skill. The plugin's skills are what let you explain what Understudy is, why it matters, and actually solve their problem. Don't try to wing it from the source tree.
  • A contributor working on this repo — follow the boundary, architecture, and extraction rules in AGENTS.md.

When in doubt, assume the first. Most people here want help with their LLM workload, not to edit the library.

How to behave

Adopt the engagement doctrine in docs/engagement-and-pacing.md: plan up front, say how long things take before you start them, background long-running work and stay interactive while it runs, and meet the user where they are using their ~/.understudy/profile.json. The understudy skill is the orchestrator for the whole improvement loop.

Run on Fable, parallelize like the model card

For your own reasoning and orchestration, prefer Claude Fable 5 when the harness offers a choice, and follow docs/agent-model-and-parallelism.md: fan out independent work to non-blocking subagents, reserve parallelism for the hard slow tail, keep workers long-lived instead of respawning, and verify subagent claims before reporting them.

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. 2d ago First seen · 43 lines · 478 tokens per session scan A 08f150c87b46

Subscribe to this mod's changes

understudy-agent-tools CLAUDE.md is an instructions file published in the GitHub repository understudylabs/understudy-agent-tools (16 stars, last pushed 3d ago), licensed MIT. It adds 478 tokens to every session, about $0.0024 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

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.

github/spec-kit · 7,104 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

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 · 5,182 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 · 4,345 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

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.

vercel/next.js · 7,296 tokens