Borrowing it
Nothing to install: this file belongs to truecourse-ai/truecourse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/truecourse-ai/truecourse/main/CLAUDE.mdgit clone --depth 1 https://github.com/truecourse-ai/truecourseWrote 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/truecourse-ai/truecourse/claude-md)<a href="https://agentmods.dev/instructions/truecourse-ai/truecourse/claude-md"><img src="https://agentmods.dev/badge/instructions/truecourse-ai/truecourse/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.
<a href="https://agentmods.dev/instructions/truecourse-ai/truecourse/claude-md"><img src="https://agentmods.dev/badge/instructions/truecourse-ai/truecourse/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01434 | $0.01434 |
| Opus 5.5 | $0.00574 | $0.00574 |
| Sonnet 5.5 | $0.00287 | $0.00287 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
truecourse 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 1mo 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TrueCourse — Claude Instructions
TrueCourse turns the documentation a team writes into tests that prove the product does what the documents promise. A workspace gathers documents from its sources, curates them into one corpus, derives a flow from what that corpus claims, writes and proves a test per flow, and runs them. The dashboard is where that is started and watched.
This file instructs; the code describes itself
What is here is what you cannot read off the tree: the rules, the decisions already made, and where to start looking. How a package works, what a function does and which job runs when are in the code, and the detail about a module belongs in the comment at the top of that module, where it moves with what it describes. So do not restate code here — a description in this file goes stale in silence, and the next session will trust it over the tree.
Rules
- No workarounds. Find and fix the root cause. No hacks, no fallbacks, no temporary patches to get past something. If it is not working, find out why.
- Dev servers belong to the user. Never start, stop or restart one. If a restart is needed, say so and leave it to them.
- Keep
README.mdtrue. A new package, endpoint or environment variable is a change to the README in the same breath. - No Claude Code session details in commits, PRs or issues. Strip any
Claude-Session:trailer or session URL before committing or opening one.
Commands
docker compose up -d # Postgres, which is the whole of the storage
TRUECOURSE_MODE=local pnpm dev # client + server, no sign-in
pnpm build # every package
pnpm test # the whole suite (vitest)
pnpm typecheck
The suite needs pnpm build once first, since tests resolve workspace packages
from dist/, and Playwright's Chromium, without which the web-driver suites
fail hard by design. Save a run's output to a file and read it back rather than
re-running with different filters.
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.
- 1mo ago Changed · +3 lines · +55 tokens per session ba0f982cf31f
- 1mo ago Changed · -73 lines · -9,077 tokens per session aa7cac8592d3
- 1mo ago Changed · +5 lines · +2,047 tokens per session 6c4f44a372dc
- 1mo ago Changed · +4 lines · +626 tokens per session 9c95b5e7f415
- 1mo ago Changed · +402 tokens per session d0c322fde3eb
- 1mo ago Changed · +20 lines · +334 tokens per session 64317a27128a
- 1mo ago Changed · +21 lines · -1,606 tokens per session 8bf8e003d805
- 1mo ago Changed · -1 lines · +338 tokens per session d4c8deb65f8e
- 1mo ago Changed · +197 tokens per session 5cf595c8f9b0
- 1mo ago First seen · 137 lines · 8,118 tokens per session scan A 23bc0d6e0667
truecourse CLAUDE.md is an instructions file published in the GitHub repository truecourse-ai/truecourse (540 stars, last pushed 15d ago), licensed MIT. It adds 1,434 tokens to every session, about $0.0057 per session on Opus 5.5. 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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.