Borrowing it
Nothing to install: this file belongs to NazarKalytiuk/tarn. 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/NazarKalytiuk/tarn/main/CLAUDE.mdgit clone --depth 1 https://github.com/NazarKalytiuk/tarnWrote 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/nazarkalytiuk/tarn/claude-md)<a href="https://agentmods.dev/instructions/nazarkalytiuk/tarn/claude-md"><img src="https://agentmods.dev/badge/instructions/nazarkalytiuk/tarn/claude-md.svg" alt="Measured on agentmods" 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 | $0.02852 | $0.02852 |
| Opus 5 | $0.01426 | $0.01426 |
| Sonnet 5 | $0.00570 | $0.00570 |
| Haiku 4.5 | $0.00285 | $0.00285 |
Grade C, and why
tarn CLAUDE.md scanned grade C with 2 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 6d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- Always verify artifacts from the real production URL/endpoint, never from local files. For install scripts: `curl <url> | sh`, not `sh ./local/path/install.sh`. For release assets: download from GitHub releases, not fr Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Always verify artifacts from the real production URL/endpoint, never from local files. For install scripts: `curl <url> | sh`, not `sh ./local/path/install.sh`. For release assets: download from GitHub releases, not fr How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Tarn is a CLI-first API testing tool written in Rust. Tests are defined in .tarn.yaml files. Designed for AI-assisted workflows: an LLM writes tests, runs tarn run, parses structured JSON output, and iterates.
Build & Run Commands
cargo build # dev build
cargo build --release # release build (single binary, zero runtime deps)
cargo run -- run # run all tests
cargo run -- run tests/x.tarn.yaml # run specific test file
cargo run -- validate # validate YAML without running
cargo run -- list # dry run listing
cargo test # run all Rust tests
cargo test parser_test # run a single test module
cargo clippy # lint
cargo fmt # format
Mandatory Pre-Commit Checks
Always run these commands before every commit and push. Do not skip them — CI will fail otherwise. This has caused repeated CI failures across multiple sessions.
cargo fmt # fix formatting FIRST
cargo clippy -- -D warnings # then fix all warnings
cargo test # then verify tests pass
Do not commit or push if any of these fail. Fix the issue, then commit.
Rules Learned From Past Mistakes
Quality gates
- Never suppress linter/clippy warnings with
#[allow(...)]. Always fix the root cause — refactor functions, extract structs, simplify signatures. Suppression is not a fix. (User explicitly rejected this approach.) - Never dismiss a failing test as "flaky" or "pre-existing" without investigating. Read the test, understand why it fails, fix it. Every test failure is a real signal until proven otherwise.
- Do not commit/push with known failing tests. If tests fail, fix them first — even if they look unrelated to your changes.
Verification
- Always verify artifacts from the real production URL/endpoint, never from local files. For install scripts:
curl <url> | sh, notsh ./local/path/install.sh. For release assets: download from GitHub releases, not from the local build. (User was frustrated twice by this.) - When writing or updating docs (README, install instructions), verify every command and URL actually works end-to-end before committing. If a doc references a binary or asset, confirm it exists in the release pipeline.
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.
- 6d ago First seen · 240 lines · 2,852 tokens per session scan C 0687d64a2dab
tarn CLAUDE.md is an instructions file published in the GitHub repository NazarKalytiuk/tarn (5 stars, last pushed 3mo ago), licensed MIT. It adds 2,852 tokens to every session, about $0.0143 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
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.
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).
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).
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.
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.