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.
npx agentmods add instructions/ytaskiran/tws/agents-mdgit clone --depth 1 https://github.com/ytaskiran/twsWrote 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/ytaskiran/tws/agents-md)<a href="https://agentmods.dev/instructions/ytaskiran/tws/agents-md"><img src="https://agentmods.dev/badge/instructions/ytaskiran/tws/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 | $0.02828 | $0.02828 |
| Opus 5 | $0.01414 | $0.01414 |
| Sonnet 5 | $0.00566 | $0.00566 |
| Haiku 4.5 | $0.00283 | $0.00283 |
Grade B, and why
tws AGENTS.md scanned grade B with 1 finding 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Hook wiring lives in `install.sh` (`status_hook_entry`, `session_end_hook_entry`). Editing it does **not** reach existing installs — the mappings are copied into `~/.claude/settings.json` at install time, so protocol cha How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to agents working in this repository.
Build & Test
cargo build # compile
cargo test # run the full test suite
cargo test state::tests # run tests in a specific module
cargo test resolve_selection # run tests matching a name pattern
CI
.github/workflows/ci.yml runs on every PR and every push to main. Five jobs, all required to pass:
cargo test --all-targets --locked # Test
cargo fmt --all --check # Rustfmt — formatting
cargo clippy --all-targets --locked -- -D warnings # Clippy — lints as errors
cargo audit # Security audit — RustSec advisories
bash scripts/verify-agent-hooks.sh # Agent hook protocol — see below
Run cargo fmt --all and cargo clippy --all-targets -- -D warnings before pushing. CI pins the toolchain to Rust 1.96.1 (see RUST_VERSION in ci.yml); rustfmt reflows and clippy lints shift between releases, so format/lint with a matching toolchain to avoid CI turning red on formatting alone.
Workflow
Every change — even a tiny one — happens in a fresh git worktree on a new branch, then goes out as a PR. Never edit and commit directly on main in the primary checkout.
git worktree add ../tws-<slug> -b <branch> origin/main
cd ../tws-<slug>
# ...edit, commit, push, gh pr create
This keeps in-flight work isolated from main, and ensures every change is reviewable on GitHub before it lands.
Release
Patch/minor/major bumps follow semver.
- Land fix/feature commits on
main(merge any feature worktrees in first — do not bump versions inside a feature branch/worktree, it causesCargo.lockconflicts on merge). - In the primary
maincheckout, bumpversionin bothCargo.tomlandCargo.lock(the[[package]] name = "tws"entry) in a separate commit titledversion bump to vX.Y.Z. - Lightweight tag at the bump commit:
git tag vX.Y.Z. Push both:git push origin main && git push origin vX.Y.Z.
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.
- 4d ago First seen · 150 lines · 2,828 tokens per session scan B 85d6e0ba5d53
tws AGENTS.md is an instructions file published in the GitHub repository ytaskiran/tws (54 stars, last pushed 12d ago), licensed MIT. It adds 2,828 tokens to every session, about $0.0141 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
agent-of-empires AGENTS.md
AGENTS.md instructions for agent-of-empires/agent-of-empires, covering repository guidelines, where to look, commands, code rules and tests.
psmux AGENTS.md
AGENTS.md instructions for psmux/psmux, covering agent instructions and test isolation.
terminal AGENTS.md
Instructions for browser-use/terminal, covering agent notes, rust rewrite verification loop and terminal ui testing standard.
hex1b AGENTS.md
Instructions for mitchdenny/hex1b, covering ai coding agent guidelines for hex1b, 🛠️ available skills, 📋 project overview, key technologies and repository layout.
unifly AGENTS.md
Instructions for hyperb1iss/unifly, covering agents.md, what this repository is, quick command reference, the canonical "before commit" gate and individual gates.
waveloom AGENTS.md
Instructions for Menfre01/waveloom, covering waveloom, 项目概要, 编码规范, 代码审查 and 开发流程.