Borrowing it
Nothing to install: this file belongs to inceptyon-labs/TARS. 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/inceptyon-labs/TARS/main/AGENTS.mdgit clone --depth 1 https://github.com/inceptyon-labs/TARSWrote 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/inceptyon-labs/tars/agents-md)<a href="https://agentmods.dev/instructions/inceptyon-labs/tars/agents-md"><img src="https://agentmods.dev/badge/instructions/inceptyon-labs/tars/agents-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 | $0.00547 | $0.00547 |
| Opus 5 | $0.00273 | $0.00273 |
| Sonnet 5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
TARS AGENTS.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 7d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TARS — agent notes
Desktop app for managing Claude Code configuration (skills, agents, commands, hooks, MCP servers, plugins, profiles). See README for features and usage.
Build & test
- Frontend lives in
apps/tars-desktop:bun install, thenbun run tauri dev/bun run tauri build. - Rust workspace:
cargo build,cargo test,cargo run -p tars-cli -- scan. - Frontend tests:
bun run test:run(Vitest + React Testing Library,*.test.ts(x)), e2ebun run test:e2e(Playwright). - Coverage:
bun run test:coverage(v8). There is no cargo tarpaulin setup. - Lint/typecheck before commit:
bun run lint,bun run typecheck,cargo fmt --all,cargo clippy --all -- -D warnings. - There is no
formatscript — Prettier runs via the pre-commit hook. Enable hooks after clone:git config core.hooksPath .githooks.
Modules
crates/tars-scanner— non-destructive discovery of config across scopes, collision detection.crates/tars-core— profiles, diff/apply/rollback engine, SQLite storage.crates/tars-providers— AI provider integrations (key validation, model discovery, pricing); consumed bysrc-tauri/src/commands/api_keys.rs.crates/tars-cli— CLI wrapper for the scanner.apps/tars-desktop/src-tauri— Tauri IPC backend over the crates.
Invariants
- Tauri commands return
Result<T, String>; frontend shows failures withtoast.error()(Sonner). Never panic in library code. unsafe_code = "forbid"workspace-wide via[workspace.lints]; clippy must pass with-D warnings.- IPC types live in
apps/tars-desktop/src/lib/types/— keep Rust and TS shapes in sync when changing commands. - Never execute code from scanned configs; validate paths against traversal and sanitize anything passed to a shell.
- Discovery-first, safe-by-default: scan before modifying; changes get diff preview, backup, and rollback.
Configuration scopes
Precedence high → low: Managed > Local > Project > User. The full per-OS path table lives in README ("Configuration Scopes") — single source, don't duplicate it here.
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.
- 7d ago First seen · 47 lines · 547 tokens per session scan A 59c313933a38
TARS AGENTS.md is an instructions file published in the GitHub repository inceptyon-labs/TARS (38 stars, last pushed 2mo ago), licensed MIT. It adds 547 tokens to every session, about $0.0027 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.
Other instructions, from other repositories
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).
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.
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 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).
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.