Borrowing it
Nothing to install: this file belongs to astetic-dev/taurus. 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/astetic-dev/taurus/main/CLAUDE.mdgit clone --depth 1 https://github.com/astetic-dev/taurusWrote 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/astetic-dev/taurus/claude-md)<a href="https://agentmods.dev/instructions/astetic-dev/taurus/claude-md"><img src="https://agentmods.dev/badge/instructions/astetic-dev/taurus/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/astetic-dev/taurus/claude-md"><img src="https://agentmods.dev/badge/instructions/astetic-dev/taurus/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 | $0.00896 | $0.00896 |
| Opus 5.5 | $0.00358 | $0.00358 |
| Sonnet 5.5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
taurus 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taurus — project instructions
Contribution workflow — changes go through GitHub issues
Every change to this project goes through a GitHub issue first. Before writing code, file (or reference) a GitHub issue that describes the problem and the intended fix; do the work on a branch and open a PR that references the issue.
- Language: English. All issues, PRs, branch names and commit messages are in English (the repo is public on GitHub). This overrides the global Dutch default for this project.
- Account:
astetic-dev([email protected]). TheghCLI is authenticated as this account; the remote ishttps://github.com/astetic-dev/taurus.git. - Create issues with
gh issue create --repo astetic-dev/taurus .... Write a long body to a temporary file outside the repo and pass it with--body-file; issue drafts, release-note drafts and status notes are never committed (release notes live on the GitHub release).
Stack
- Tauri v2; frontend = vanilla JS under
src/(frontendDist: ../src); Rust undersrc-tauri/. - Platforms: Windows is the primary target; the macOS port is tracked in #199. Keep one
codebase: platform differences go behind
cfggates or a small platform module, and every change keeps the Windows build working.
Working agreements
These come from working on this project with its owner (Arjen). They hold on every machine.
- Finish a theme into one working build. Issues and PRs are the agent's bookkeeping,
not the owner's homework: merge to
main, push, close the PR and the issues that are done. Don't deliver a stack of branches with "these are still open, please merge". Mention once at the end what was deliberately not built; don't end on an open question. - Version numbers only on request. Feedback goes into builds without touching the
version in
src-tauri/Cargo.toml/src-tauri/tauri.conf.json. When a release is asked for, bump conservatively (patch by default; minor only for a substantial feature set) and confirm the exact number before releasing. - Shared working tree: check the branch. More than one agent session can work in the
same checkout. Run
git branch --show-currentbefore the first change and again beforegit add. If it isn't yours, save your patch (git diff > file), restore the tree as you found it, and continue in your own worktree (git worktree add ../Taurus-<topic> -b <branch> origin/main). Remove it afterwards. - Never start, close or kill the owner's Taurus window. The agent session is often
running inside it, and a test instance disappearing mid-test looks like a broken build.
On Windows a running exe is locked, so build into a fresh
targetdirectory and ask the owner to restart their own window. - Commands for the owner go in a
.mdfile that is not committed (e.g. under the gitignoredinput/), one command per fenced block, with the full path mentioned in the reply. Copying commands out of the terminal chat adds spaces and CRLFs. Test plans that need a second machine go into a comment on their issue, with checkboxes; measure the local half yourself and put it in unit tests. - A measured limitation is a fact, not a design requirement. Taurus works where it can; a stricter environment is that user's problem. Report the limitation in one honest line and offer the normal path as the normal path. Do build what is correct anyway and costs nothing.
- Screenshots: only the Taurus window, never the full screen. The owner's desktop can show password managers and customer data. Delete verification screenshots afterwards.
- Measured pitfalls live in
PITFALLS.md. Read the section for the area you touch before changing it. Add to it when you measure a new one.
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 · +1 lines · +21 tokens per session 1ff8a6b51c1d
- 1mo ago Changed · +37 lines · +624 tokens per session cf8a393896ed
- 2mo ago First seen · 19 lines · 251 tokens per session scan A 064c2840d596
taurus CLAUDE.md is an instructions file published in the GitHub repository astetic-dev/taurus (5 stars, last pushed 15d ago), licensed MIT. It adds 896 tokens to every session, about $0.0036 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 2026-08-31.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.