measuring-ai-proficiency AGENTS.md

measuring-ai-proficiency AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from pskoett/measuring-ai-proficiency. It costs 3,937 tokens per session, scanned A, original, MIT.

Agent-role instructions for measure-ai-proficiency, a Python command-line tool that measures the quality of AI coding instructions in repositories. They assign separate responsibilities for coding, documentation, and skill development.

In plain words
What is it for?
Implementing features or fixes, updating scanner and report modules, maintaining documentation, and synchronizing skill files.
Why use it?
They set shared expectations for supported Python versions, typing, tests, documentation, and compatibility. This reduces inconsistent changes across the tool's modules and instruction files.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: PostToolUse hook event, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

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/pskoett/measuring-ai-proficiency/agents-md
Clone the repo
git clone --depth 1 https://github.com/pskoett/measuring-ai-proficiency

Made for: Claude Code, Codex, OpenCode.

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 measuring-ai-proficiency AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pskoett/measuring-ai-proficiency/agents-md.svg)](https://agentmods.dev/instructions/pskoett/measuring-ai-proficiency/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/pskoett/measuring-ai-proficiency/agents-md"><img src="https://agentmods.dev/badge/instructions/pskoett/measuring-ai-proficiency/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,937 This file is loaded in full into every session.
When invoked 3,937 The same file — it is already loaded in full.
Security scan A 0 findings. 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 5.1 $0.03937 $0.03937
Opus 5 $0.01969 $0.01969
Sonnet 5 $0.00787 $0.00787
Haiku 4.5 $0.00394 $0.00394

Measured 6d ago against content hash de9a03a356bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

measuring-ai-proficiency 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 6d 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.

AGENTS.md · 311 lines

How it starts

The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents

This document defines agent roles, behavioral guidelines, and factory chain context for AI assistants working on the measure-ai-proficiency project.

Agent Roles

Code Implementer

Purpose: Implement features, fix bugs, and maintain the codebase.

Key behaviors:

  • Follow pure Python conventions (no external dependencies for core functionality)
  • Use type hints on all functions and methods
  • Use dataclasses for data structures
  • Maintain backwards compatibility with Python 3.9+
  • Run pytest tests/ -v before committing changes

Files to modify:

  • measure_ai_proficiency/scanner.py - Core scanning logic
  • measure_ai_proficiency/config.py - Level definitions and patterns
  • measure_ai_proficiency/reporter.py - Output formatting
  • measure_ai_proficiency/repo_config.py - Configuration handling
  • measure_ai_proficiency/github_scanner.py - GitHub CLI integration

Documentation Writer

Purpose: Keep documentation accurate and helpful.

Key behaviors:

  • Update README.md when features change
  • Keep docs/CUSTOMIZATION.md current with config options
  • Sync skill files across all locations when updating:
    • .claude/skills/*/SKILL.md
    • .github/skills/*/SKILL.md
    • skill-template/*/SKILL.md
  • Update .ai-proficiency.yaml.example when adding config options

Constraints:

  • Never add features to docs that don't exist in code
  • Always include examples with documentation
  • Keep the example output in README.md current

Skill Developer

Purpose: Create and maintain agent skills for this tool.

Key behaviors:

  • Skills should be self-contained and follow the Agent Skills standard
  • Include clear triggers and workflow steps
  • Test skills work with both Claude Code and GitHub Copilot
  • Sync skills to all three locations after changes

Available skills:

  • measure-ai-proficiency - Run assessments
  • customize-measurement - Configure for specific repos
  • plan-interview - Interview-based planning
  • agentic-workflow - GitHub agentic workflow creation
  • self-improvement - Learning capture and prevention rule promotion

Read the full file on GitHub · 311 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. 6d ago First seen · 311 lines · 3,937 tokens per session scan A de9a03a356bc

Subscribe to this mod's changes

measuring-ai-proficiency AGENTS.md is an instructions file published in the GitHub repository pskoett/measuring-ai-proficiency (10 stars, last pushed 1mo ago), licensed MIT. It adds 3,937 tokens to every session, about $0.0197 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 2026-08-31.

Related

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).

microsoft/vscode · 6,785 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens