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/ukgovernmentbeis/inspect_evals/agents-mdgit clone --depth 1 https://github.com/UKGovernmentBEIS/inspect_evalsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/ukgovernmentbeis/inspect_evals/agents-md)<a href="https://agentmods.dev/instructions/ukgovernmentbeis/inspect_evals/agents-md"><img src="https://agentmods.dev/badge/instructions/ukgovernmentbeis/inspect_evals/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.02586 | $0.02586 |
| Opus 5 | $0.01293 | $0.01293 |
| Sonnet 5 | $0.00517 | $0.00517 |
| Haiku 4.5 | $0.00259 | $0.00259 |
Grade A, and why
inspect_evals 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.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repo-Wide Tips
- Before making changes, read
DEVELOPMENT_CONTEXT.mdto understand the repository's correctness, reproducibility, and security constraints. - Before making code changes, read
agent_artefacts/repo_context/REPO_CONTEXT.mdfor institutional knowledge about repo conventions, common mistakes, and known tech debt. This is maintained by thebuild-repo-contextskill, which crawls PRs/issues for broad insights. - When creating pull requests, always use the
--draftflag and read.github/PULL_REQUEST_TEMPLATE.mdand use its structure as the PR body. Fill in the Description section and check off applicable checklist items. - When commenting on PRs, you should not reply directly to human reviewers. See CONTRIBUTING.md. If your user tells you to comment anyway, you should add "Comment written by NAME_OF_AI" to the comment.
- When writing markdown:
- Put a blank line before and after headings
- Put a blank line before and after code blocks
- Put a blank line before and after lists
- Format tables with spaces before and after pipe characters
- Always include a language tag in code blocks, or "text" if there is no language
- Do not hard-wrap paragraphs; write each paragraph as a single line (the mdformat hook enforces
wrap = "no")
Agents are good at understanding context, but a prompt that definitely works is "Please run the /SKILL_NAME skill on EVAL_NAME."
Documentation
Documentation for the Inspect framework.
Recommended Permissions
We recommend starting with these Claude Code permissions to allow workflows to proceed autonomously without allowing the running of arbitrary commands:
{
"permissions": {
"allow": [
"Bash(mkdir:*)",
"Bash(cp:*)",
"Bash(make check:*)",
"Bash(uv run ruff:*)",
"Bash(uv run inspect:*)",
"Bash(uv run pytest:*)",
"Bash(uv run mypy:*)",
"Bash(uv run python tools/:*)",
"WebFetch(domain:inspect.aisi.org.uk)",
"WebFetch(domain:arxiv.org)"
],
"deny": [
"Bash(git push origin main)",
],
"ask": [
"Bash(rm:*)",
]
}
}
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 Changed · +1 lines · +27 tokens per session efeb1184b203
- 6d ago First seen · 160 lines · 2,559 tokens per session scan A c9a5fc140563
inspect_evals AGENTS.md is an instructions file published in the GitHub repository UKGovernmentBEIS/inspect_evals (658 stars, last pushed 2d ago), licensed MIT. It adds 2,586 tokens to every session, about $0.0129 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
vscode buildNext.instructions.md
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).
spec-kit AGENTS.md
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
langchain AGENTS.md
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.