What is ts-bench copilot-instructions.md?

Contributor instructions for ts-bench, a command-line benchmark for comparing AI coding agents on TypeScript tasks. They specify the runtime, testing rules, agent registration, authentication setup, and Docker requirements.

Use them to add agents, run tests, set up authentication, prepare the Docker environment for v2, and follow the project's pull-request rules.

They prevent contributors from using the wrong commands or missing required tests and environment setup.

ts-bench copilot-instructions.md — Instructions file by laiso

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/copilot-instructions

Clone the repo

git clone --depth 1 https://github.com/laiso/ts-bench

Made for: GitHub Copilot.

Per session 230 This file is loaded in full into every session.

When invoked 230 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.

Model	Per session	Once invoked
Fable 5	$0.00230	$0.00230
Opus 5	$0.00115	$0.00115
Sonnet 5	$0.00046	$0.00046
Haiku 4.5	$0.00023	$0.00023

Measured 2d ago against content hash 24405f061a71, 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 copilot-instructions.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.

.github/copilot-instructions.md · 12 lines

What it actually says

Copilot Instructions for ts-bench

Always use bun, never node or npm run.

Any new or changed code must include tests. Run bun test ./src and confirm all pass.
Exercism placeholder code is intentionally broken; --test-only failures on unmodified exercises are expected.
Exercise tests use Yarn v4 (corepack yarn). Install corepack if missing: npm install -g [email protected] && corepack enable.
To add an agent: add a builder in src/agents/builders/ and register it in src/agents/factory.ts.
v2 (SWE-Lancer) requires Docker. One-time setup: ./scripts/setup-v2-env.sh. Image: swelancer/swelancer_x86_monolith:releasev1 (~15 GB).
Subscription-based auth (no API key) for Claude, Gemini, Codex: bun src/index.ts --setup-auth <agent>.
All pull request titles and descriptions must be written in English.

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.

2d ago First seen · 12 lines · 230 tokens per session scan A 24405f061a71

Subscribe to this mod's changes

ts-bench copilot-instructions.md is an instructions file published in the GitHub repository laiso/ts-bench (240 stars, last pushed 18d ago), licensed MIT. It adds 230 tokens to every session, about $0.0011 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.

LLM Languages Testing TypeScript ai-agents

zod AGENTS.md

Instructions for colinhacks/zod, covering agents.md, development commands, rules, the three axes and benchmarking traps.

colinhacks/zod · 5,774 tokens

microsandbox AGENTS.md

AGENTS.md instructions for superradcompany/microsandbox, covering agents.md, scope, project map, design principles and backward compatibility review.

superradcompany/microsandbox · 3,652 tokens

fallow

Rust-native codebase analyzer for TypeScript and JavaScript projects.

fallow-rs/fallow · 1,127 tokens

trigger.dev copilot-instructions.md

Copilot instructions for triggerdotdev/trigger.dev: This is the repo for Trigger.dev, a background jobs platform written in TypeScript. Our webapp at apps/webapp is a Remix 2.1 app that uses Node.js v20. Our SDK is an isomorphic TypeScript SDK at packages/trigger-sdk. Always prefer using isomorphic code like fetch…

triggerdotdev/trigger.dev · 140 tokens

starknet.js AGENTS.md

Instructions for starknet-io/starknet.js, covering agents.md, setup & core commands, verifying your changes (read this before running tests), architecture map (src/) and conventions.

starknet-io/starknet.js · 1,748 tokens

effection AGENTS.md

Instructions for thefrontside/effection, covering agents.md — effection agent contract, core invariants (do not violate), operations vs promises, structured concurrency is scope-owned and effects do not escape scopes.

thefrontside/effection · 3,630 tokens