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/laiso/ts-bench/agents-mdgit clone --depth 1 https://github.com/laiso/ts-benchWhat 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 | $0.00113 | $0.00113 |
| Opus 5 | $0.00056 | $0.00056 |
| Sonnet 5 | $0.00023 | $0.00023 |
| Haiku 4.5 | $0.00011 | $0.00011 |
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.
What it actually says
AGENTS.md
ts-bench: TypeScript AI Agent Benchmark CLI (Bun). See README.md, specs/000-project-handbook/.
- Always use
bun— nevernode/npm run. Runbun test ./srcfor all changes and confirm pass. - Exercism placeholder code is intentionally broken;
--test-onlyfailures are expected. - v2 (SWE-Lancer): Docker required, ~15 GB image. Run
./scripts/setup-v2-env.shonce.
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 · 8 lines · 113 tokens per session scan A f774aad3d439
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.
Other instructions, from other repositories
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
airi copilot-instructions.md
Copilot instructions for moeru-ai/airi, covering copilot repository instructions, general rules, validation and output format.
entroly CLAUDE.md
Instructions for juyterman1000/entroly, covering claude.md, gstack operating protocol, default workflow, entroly trust invariants and review checklist.
autonomous-os AGENTS.md
Instructions for autonomous-ai/autonomous-os, covering agents.md, multi-ide rules, working style, parallel work / subagents and device access rules.
spellbook AGENTS.md
Instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.
Codex-Skills AGENTS.md
Instructions for TheGoat395/Codex-Skills, covering repository operating notes, required checks, evidence rules and change hygiene.