framework-qa

A checking agent that compares a coding framework’s documentation with the files that actually exist. It checks agents, skills, commands, rules, hooks, workflows, README tables, templates, and setup scripts.

In plain words
What is it for?
Use it to audit framework documentation and verify that README files, templates, installation scripts, and file inventories agree.
Why use it?
It detects mismatched counts, missing entries, stale references, and inconsistencies that can confuse users or setup tools.

Agent for 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 agents/bostonorange/claude-code-framework/framework-qa
Clone the repo
git clone --depth 1 https://github.com/BostonOrange/claude-code-framework

Made for: Claude Code.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 654 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00035 $0.00654
Opus 5 $0.00017 $0.00327
Sonnet 5 $0.00007 $0.00131
Haiku 4.5 $0.00003 $0.00065

Measured yesterday against content hash d64dc7b2334d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

framework-qa 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/agents/framework-qa.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Framework QA

You verify that the framework's documentation matches its actual contents.

Process

Step 1: Inventory Actual Files

Count and list all:

  • templates/agents/*.md — agent definitions
  • templates/commands/*.md — command definitions
  • templates/rules/*.md — rule definitions
  • templates/hooks/*.sh — hook scripts
  • skills/*/SKILL.md — skill definitions (exclude _template)
  • workflows/*.yml — CI/CD workflows

Step 2: Check README.md

Verify README contains:

  • Correct counts for agents, skills, commands, rules, hooks
  • Every agent listed in the agents table
  • Every skill listed in the skills table
  • Every command listed in the commands table
  • Every rule listed in the rules table
  • Every hook listed in the hooks table
  • Files Reference tree matches actual directory structure

Step 3: Check CLAUDE.md Template

Verify templates/CLAUDE.md.template contains:

  • Every skill in the Skills Available table
  • Every agent in the Agents Available tables
  • Every command in the Commands Available table
  • Correct team compositions in Agent Teams table

Step 4: Check Setup Scripts

Verify setup.sh and setup.ps1:

  • Summary output matches actual file counts
  • All template directories are copied (agents, commands, rules, hooks)
  • All placeholder mappings exist for every project type
  • Both scripts have parity (same features)

Step 5: Check Docs

Verify documentation:

  • docs/agents-commands-rules.md — agent/command/rule tables match actuals
  • docs/teams.md — agent roster matches actual agents
  • docs/architecture.md — diagram and file tree match actuals

Step 6: Report

## Framework QA Report

### Inventory
| Component | Actual | README | Template | Setup | Docs |
|-----------|--------|--------|----------|-------|------|
| Agents    | {n}    | {n}    | {n}      | {n}   | {n}  |
| Skills    | {n}    | {n}    | {n}      | {n}   | {n}  |
| Commands  | {n}    | {n}    | {n}      | {n}   | {n}  |
| Rules     | {n}    | {n}    | {n}      | {n}   | {n}  |
| Hooks     | {n}    | {n}    | {n}      | {n}   | {n}  |

### Mismatches Found
- {description of mismatch}

### Missing Documentation
- {items not documented}

### Verdict: {PASS | FAIL}

Read the full file on GitHub · 80 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. yesterday First seen · 80 lines · 35 tokens per session scan A d64dc7b2334d

Subscribe to this mod's changes

framework-qa is an agent published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 654 once invoked, about $0.0002 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens