agentmods.dev

reforge-ai-evals: Instructions file for Claude Code

CLAUDE.md

reforge-ai-evals CLAUDE.md is an instructions file for Claude Code from Calibre-Labs/reforge-ai-evals. It costs 255 tokens per session, scanned A, original, MIT.

A set of repository instructions for the reforge-ai-evals project. It explains when to change plugin versions and how to keep the two plugin manifests consistent.

In plain words
What is it for?
It is for maintaining a Claude Code or Codex plugin repository, especially when changing skills, templates, scripts, or plugin manifests.
Why use it?
It prevents code changes from being merged without a version update that users need in order to receive them. It also defines which version change is appropriate for each kind of change.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions .claude-plugin; mentions Claude Code; mentions Codex.

This is Calibre-Labs/reforge-ai-evals's own configuration. It tells Claude Code how to work on reforge-ai-evals itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything reforge-ai-evals configures →

not rated 95repo +1 yesterday A scan 255 tokens original MIT
View source ↗ Calibre-Labs/reforge-ai-evals reforge.com
Reuse

Borrowing it

Nothing to install: this file belongs to Calibre-Labs/reforge-ai-evals. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Calibre-Labs/reforge-ai-evals/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Calibre-Labs/reforge-ai-evals

Made for: Claude Code.

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 reforge-ai-evals CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/calibre-labs/reforge-ai-evals/claude-md/github.svg)](https://agentmods.dev/instructions/calibre-labs/reforge-ai-evals/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/calibre-labs/reforge-ai-evals/claude-md"><img src="https://agentmods.dev/badge/instructions/calibre-labs/reforge-ai-evals/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for reforge-ai-evals CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/calibre-labs/reforge-ai-evals/claude-md"><img src="https://agentmods.dev/badge/instructions/calibre-labs/reforge-ai-evals/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 255 This file is loaded in full into every session.
When invoked 255 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00255 $0.00255
Opus 5.5 $0.00102 $0.00102
Sonnet 5.5 $0.00051 $0.00051
Haiku 4.5 $0.00026 $0.00026

Measured yesterday against content hash e4c884456bb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

reforge-ai-evals 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 yesterday.

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.

CLAUDE.md · 17 lines

What it actually says

reforge-ai-evals

Plugin versions

Claude Code and Claude desktop install this plugin from this repo and update it only when its version changes. A merged change without a bump never reaches anyone. So every PR that changes the plugin bumps the version exactly once.

  • Bump when the PR changes what users get: anything under skills/, templates/ or scripts/, or the plugin manifests. Don't bump for repo-only changes (docs/, the README, llms.txt, CITATION.cff, this file).
  • Which number (semver):
    • patch (x.y.Z): fixes, wording, small tweaks to an existing skill or script
    • minor (x.Y.0): a new skill, script, option or behavior
    • major (X.0.0): a removed or renamed skill, or a change that breaks existing files, commands or workflows
  • Where: .claude-plugin/plugin.json and .codex-plugin/plugin.json. Keep them identical.
  • If main moves first: when another PR merges with the same or a higher version, re-bump above main before merging.
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. yesterday First seen · 17 lines · 255 tokens per session scan A e4c884456bb1

Subscribe to this mod's changes

reforge-ai-evals CLAUDE.md is an instructions file published in the GitHub repository Calibre-Labs/reforge-ai-evals (95 stars, last pushed yesterday), licensed MIT. It adds 255 tokens to every session, about $0.0010 per session on Opus 5.5. 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 2026-11-07.

Git and workflowReleasesagent-evaluationai-evalsai-product-managementbraintrustclaude-skills
Related

reforge-ai-evals CLAUDE.md compared with instructions from other repositories

reforge-ai-evals CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
reforge-ai-evals CLAUDE.mdCalibre-Labs/reforge-ai-evalsInstructions file95yesterdayMITA255Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot