openadapt-evals CLAUDE.md

openadapt-evals CLAUDE.md is an instructions file for coding agents from OpenAdaptAI/openadapt-evals. It costs 10,026 tokens per session, scanned C, original, MIT.

A project instruction file for OpenAdaptAI/openadapt-evals that defines required Git branches, pull requests, commit titles, project status, and safe handling of worktrees, separate working directories for Git branches.

In plain words
What is it for?
Use it when contributing to that project to create a feature branch, submit changes through a pull request, follow naming rules, and avoid deleting worktrees without checking.
Why use it?
It prevents direct changes to the main branch and accidental removal of another agent's working directory or uncommitted work.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/openadaptai/openadapt-evals/claude-md
Clone the repo
git clone --depth 1 https://github.com/OpenAdaptAI/openadapt-evals

Wrote 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.

agentmods badge for openadapt-evals CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/openadaptai/openadapt-evals/claude-md.svg)](https://agentmods.dev/instructions/openadaptai/openadapt-evals/claude-md)
Your own site
<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>
Per session 10,026 This file is loaded in full into every session.
When invoked 10,026 The same file — it is already loaded in full.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash d8f09c24c16a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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/`.
CLAUDE.md · 973 lines

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.

  1. Create a feature branch: git checkout -b feat/description or fix/description
  2. Make commits on the branch
  3. Push the branch: git push -u origin branch-name
  4. Create a PR: gh pr create --title "..." --body "..."
  5. 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:

  1. Ask the user if other agents/sessions are running
  2. Only remove worktrees you created in this session
  3. 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 endpoint
  • feat: add demo-conditioned evaluation script
  • fix(agent): return error instead of done on CU agent failures

Read the full file on GitHub · 973 lines

Changes

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.

  1. 4d ago First seen · 973 lines · 10,026 tokens per session scan C d8f09c24c16a

Subscribe to this mod's changes

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.