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/openadaptai/openadapt-evals/claude-mdgit clone --depth 1 https://github.com/OpenAdaptAI/openadapt-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/openadaptai/openadapt-evals/claude-md)<a href="https://agentmods.dev/instructions/openadaptai/openadapt-evals/claude-md"><img src="https://agentmods.dev/badge/instructions/openadaptai/openadapt-evals/claude-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 | $0.10026 | $0.10026 |
| Opus 5 | $0.05013 | $0.05013 |
| Sonnet 5 | $0.02005 | $0.02005 |
| Haiku 4.5 | $0.01003 | $0.01003 |
Grade C, and why
openadapt-evals CLAUDE.md scanned grade C with 1 finding 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
This rule also applies to `git clean`, `rm -rf` on worktree paths, and any operation that deletes directories under `.claude/worktrees/`. How it starts
The opening of the file, as written. The whole thing — 973 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Instructions for openadapt-evals
MANDATORY: Branches and Pull Requests
NEVER push directly to main. ALWAYS use feature branches and pull requests.
- Create a feature branch:
git checkout -b feat/descriptionorfix/description - Make commits on the branch
- Push the branch:
git push -u origin branch-name - Create a PR:
gh pr create --title "..." --body "..." - Only merge via PR (never
git push origin main)
This is a hard rule with NO exceptions, even for "small" changes.
MANDATORY: Never Remove Worktrees You Didn't Create
NEVER run git worktree remove or git worktree prune without confirming no other sessions are using them.
Removing a worktree that another Claude session is using as its working directory kills that session permanently — every command fails with "Working directory no longer exists" and the session cannot recover. Uncommitted work is lost.
Before removing ANY worktree:
- Ask the user if other agents/sessions are running
- Only remove worktrees you created in this session
- Never batch-remove worktrees — each one could be another session's home
This rule also applies to git clean, rm -rf on worktree paths, and any operation that deletes directories under .claude/worktrees/.
PR Titles MUST Use Conventional Commit Format
PR titles become the squash merge commit message on main. python-semantic-release parses these to decide version bumps. If the PR title doesn't follow the format, no release is created.
fix: short description → patch bump (0.0.x)
feat: short description → minor bump (0.x.0)
fix(scope): short description → patch bump with scope
feat!: breaking change → major bump (x.0.0)
Types: feat, fix, docs, style, refactor, perf, test, chore, ci
Rules: Lowercase type, colon+space, imperative mood, no period, max 72 chars.
Examples:
fix: guard empty metric_results in evaluate endpointfeat: add demo-conditioned evaluation scriptfix(agent): return error instead of done on CU agent failures
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.
- 4d ago First seen · 973 lines · 10,026 tokens per session scan C d8f09c24c16a
openadapt-evals CLAUDE.md is an instructions file published in the GitHub repository OpenAdaptAI/openadapt-evals (3 stars, last pushed today), licensed MIT. It adds 10,026 tokens to every session, about $0.0501 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
agentinsight-sdk-python AGENTS.md
Instructions for AgentInsight/agentinsight-sdk-python, covering agentinsight python sdk — 智能体执行规则, 1. 项目基本信息, 1.1 技术栈, 1.2 项目关键特征 and 1.3 项目目录结构.
deepagents AGENTS.md
AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
apm python.instructions.md
Python development guidelines.
lobster0 AGENTS.md
AGENTS.md instructions for NEDONION/lobster0, covering lobster0 agent 工程规范, 适用范围与优先级, 项目事实, 常用命令 and 首次安装或依赖变化后.
streamlit e2e_playwright.instructions.md
Instructions for streamlit/streamlit, covering streamlit e2e tests, test structure, key fixtures and utilities, external test mode and url handling (no localhost hardcoding).
pydantic-ai-gepa AGENTS.md
AGENTS.md instructions for indexedlabs/pydantic-ai-gepa, covering repository guidelines, mighty workflow, project structure & module organization, build, test, and development commands and coding style & naming conventions.