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/lukasmetzler/agenteval/copilot-instructionsgit clone --depth 1 https://github.com/lukasmetzler/agentevalWhat 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 | $0.00110 | $0.00110 |
| Opus 5 | $0.00055 | $0.00055 |
| Sonnet 5 | $0.00022 | $0.00022 |
| Haiku 4.5 | $0.00011 | $0.00011 |
Grade A, and why
agenteval 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.
What it actually says
Copilot Instructions
Language
TypeScript with strict mode. Bun runtime. Tabs for indentation.
Rules
- Always add JSDoc comments to exported functions
- Use
readonlyarrays where possible - Prefer
interfaceovertypefor object shapes - Use
satisfiesoperator for type narrowing - Never use
enum-- useas constobjects instead
Suggestions
Be careful with error handling. Make sure to handle all edge cases. Read this carefully and follow all instructions precisely.
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 · 19 lines · 110 tokens per session scan A 32e9c43f27a9
agenteval copilot-instructions.md is an instructions file published in the GitHub repository lukasmetzler/agenteval (6 stars, last pushed 2mo ago), licensed MIT. It adds 110 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 2026-08-31.
Other instructions, from other repositories
mobilegym AGENTS.md
Instructions for Purewhiter/mobilegym, covering agents.md, project overview, type-checking strategy, eslint and with data graph generation.
opengeni AGENTS.md
Instructions for Cloudgeni-ai/opengeni, covering agent / automation notes (opengeni), full local stack, architecture notes, pull-request delivery across moving main and keeping these notes current.
hivekeep CLAUDE.md
Instructions for MarlBurroW/hivekeep, covering hivekeep, documentation map, tech stack, key conventions and naming.
sixb AGENTS.md
Instructions for sixb-ai/sixb, covering agents.md, scope, repo map, toolchain and core commands.
agent-belt AGENTS.md
Instructions for jfrog/agent-belt, covering agent-belt - guide for ai coding agents, 1. what this is, 2. setup & first verification, 3. where to start (by task) and 4. design principles.
useagent CLAUDE.md
Claude Code instructions for useagenthq/useagent, covering useagent - claude.md and hard rules.