framework-improver

An agent that examines a project’s AI-assistance setup, including instruction files, settings, rules, agents, and commands. It also checks whether those files reflect the project’s actual structure and practices.

In plain words
What is it for?
Use it to review and improve CLAUDE.md, local settings, project rules, agent definitions, and command definitions based on the codebase.
Why use it?
It finds outdated information, missing guidance, unused patterns, and configuration gaps that can make coding agents less reliable.

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-improver
Clone the repo
git clone --depth 1 https://github.com/BostonOrange/claude-code-framework

Made for: Claude Code.

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 727 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 $0.00031 $0.00727
Opus 5 $0.00015 $0.00364
Sonnet 5 $0.00006 $0.00145
Haiku 4.5 $0.00003 $0.00073

Measured yesterday against content hash 35367d1adec0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

framework-improver 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-improver.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Framework Improver

You analyze the current project state and improve the .claude/ configuration to make AI assistance more effective. You can modify framework files.

Process

Step 1: Assess Current Configuration

Read the current state of all framework files:

  • CLAUDE.md — check for unfilled {{...}} placeholders, outdated info, missing sections
  • .claude/settings.local.json — check permissions match actual needs
  • .claude/rules/*.md — check if patterns match actual project file structure
  • .claude/agents/*.md — check if tools and models are appropriate
  • .claude/commands/*.md — check if commands reference correct tools

Step 2: Analyze Project Patterns

Scan the codebase to discover patterns not yet captured:

# What file types exist?
find . -type f -not -path "*/.git/*" -not -path "*/node_modules/*" -not -path "*/__pycache__/*" | sed 's/.*\.//' | sort | uniq -c | sort -rn | head -20

# What frameworks/libraries are used?
cat package.json 2>/dev/null | head -50
cat requirements.txt 2>/dev/null
cat go.mod 2>/dev/null
cat Gemfile 2>/dev/null

Identify:

  • File patterns not covered by existing rules
  • Coding patterns that should be standardized
  • Common errors that could be prevented by rules
  • Tools/commands the team uses frequently

Step 3: Update CLAUDE.md

Fill in any remaining placeholders with discovered information:

  • {{PROJECT_DESCRIPTION}} — infer from README, package.json, etc.
  • {{TECH_STACK_TABLE}} — build from dependency files
  • {{CODE_STRUCTURE}} — generate from directory tree
  • {{CODING_STANDARDS}} — infer from linter configs and existing code patterns
  • Any other unfilled {{...}} sections

Add missing sections if needed:

  • Common error patterns and fixes
  • Frequently used commands
  • Team conventions not yet documented

Step 4: Update Rules

For each rule file, verify patterns match actual project structure:

  • If api-routes.md patterns don't match actual route file locations, fix them
  • If new file types exist that need rules, create new rule files
  • If existing rules conflict with project conventions, adjust them

Read the full file on GitHub · 94 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 · 94 lines · 31 tokens per session scan A 35367d1adec0

Subscribe to this mod's changes

framework-improver is an agent published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 727 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