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/microsoft/eval-guide/claude-mdgit clone --depth 1 https://github.com/microsoft/eval-guideWhat 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 | $0.01575 | $0.01575 |
| Opus 5 | $0.00788 | $0.00788 |
| Sonnet 5 | $0.00315 | $0.00315 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
eval-guide CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repo is
This is a content/plugin repository, not an application. It ships an AI-agent evaluation toolkit for Copilot Studio in two parallel forms:
- Claude Code plugin — skills under
skills/*/SKILL.md, registered via.claude-plugin/plugin.jsonandmarketplace.json. - GitHub Copilot prompts — equivalent prompts under
.github/prompts/*.prompt.md, with always-on instructions in.github/copilot-instructions.md.
There is no build, no test runner, no lint step. Changes are validated by running the skills end-to-end against an agent description.
AGENTS.md is the master cross-tool instruction file. README.md is the canonical user-facing docs. When changing user-visible behavior, keep all three (README.md, AGENTS.md, .github/copilot-instructions.md) in sync — they each describe the same routing table for a different audience.
High-level architecture
The 6 skills form a pipeline, not a flat catalog
/eval-guide is the orchestrator that walks the customer through the operational workflow (Discover → Plan → Generate → Run → Interpret) over Microsoft's Practical Guidance on Agent Evaluation — 10-step playbook. The canonical methodology spine is skills/eval-guide/playbook.md; every skill points to it rather than restating the methodology. The other 5 skills are extracted stages that can be invoked directly:
| Skill | Role |
|---|---|
eval-guide |
Orchestrator. Owns the dashboard workflow and stage transitions. |
eval-suite-planner |
Stage 1 standalone. Produces eval-suite workbook plus an interactive HTML review page. |
eval-generator |
Stage 2 standalone. Produces test-case CSVs / conversation blueprints. |
eval-result-interpreter |
Stage 4 standalone. SHIP/ITERATE/BLOCK verdict from results. |
eval-triage-and-improvement |
Stage 4 deep-dive. Interactive remediation. |
eval-faq |
Methodology Q&A grounded in Microsoft's eval ecosystem. |
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 · 73 lines · 1,575 tokens per session scan A 761c3bfeced5
eval-guide CLAUDE.md is an instructions file published in the GitHub repository microsoft/eval-guide (127 stars, last pushed 2mo ago), licensed MIT. It adds 1,575 tokens to every session, about $0.0079 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.