ts-bench AGENTS.md

Project instructions for ts-bench, a Bun-based command-line benchmark that compares AI coding agents on TypeScript work.

In plain words
What is it for?
Use them when changing the project: run commands with Bun, execute the main test suite, understand the expected Exercism placeholder failures, and prepare the optional v2 environment.
Why use it?
They keep contributors using the required tooling and clarify which test failures are intentional and when Docker setup is needed.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/laiso/ts-bench/agents-md
Clone the repo
git clone --depth 1 https://github.com/laiso/ts-bench

Made for: Codex, OpenCode.

Per session 113 This file is loaded in full into every session.
When invoked 113 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00113 $0.00113
Opus 5 $0.00056 $0.00056
Sonnet 5 $0.00023 $0.00023
Haiku 4.5 $0.00011 $0.00011

Measured 2d ago against content hash f774aad3d439, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ts-bench 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 2d 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.

AGENTS.md · 8 lines

What it actually says

AGENTS.md

ts-bench: TypeScript AI Agent Benchmark CLI (Bun). See README.md, specs/000-project-handbook/.

  • Always use bun — never node/npm run. Run bun test ./src for all changes and confirm pass.
  • Exercism placeholder code is intentionally broken; --test-only failures are expected.
  • v2 (SWE-Lancer): Docker required, ~15 GB image. Run ./scripts/setup-v2-env.sh once.
Changes

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.

  1. 2d ago First seen · 8 lines · 113 tokens per session scan A f774aad3d439

Subscribe to this mod's changes

ts-bench AGENTS.md is an instructions file published in the GitHub repository laiso/ts-bench (240 stars, last pushed 18d ago), licensed MIT. It adds 113 tokens to every session, about $0.0006 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.