repository-improvement-agent

repository-improvement-agent is an agent for Claude Code from richfrem/agent-plugins-skills. It costs 30 tokens per session (265 once invoked), scanned A, original, MIT.

An agent that turns reports about repeated problems in a code repository into larger refactoring proposals and pull requests. A monorepo is one repository containing multiple related projects or components.

In plain words
What is it for?
Use it to review hotspot reports, identify architectural debt, plan systemic refactors, and prepare changes for issue, pull-request, and test-review workflows.
Why use it?
It helps address the shared architectural cause of recurring failures instead of fixing the same type of problem one component at a time.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agent-agentic-os plugin — 25 skills, 4 commands, 6 agents, 3 hooks shipped together

Good fit Use it to review hotspot reports, identify architectural debt, plan systemic refactors, and prepare changes for issue, pull-request, and test-review workflows.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/richfrem/agent-plugins-skills/repository-improvement-agent
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.

Clone the repo
git clone --depth 1 https://github.com/richfrem/agent-plugins-skills

Made for: Claude Code.

Or install agent-agentic-os, the plugin that ships this one along with the rest of its 25 skills, 4 commands, 6 agents, 3 hooks.

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 repository-improvement-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/repository-improvement-agent.svg)](https://agentmods.dev/agents/richfrem/agent-plugins-skills/repository-improvement-agent)
Your own site
<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/repository-improvement-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/repository-improvement-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 265 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00030 $0.00265
Opus 5 $0.00015 $0.00133
Sonnet 5 $0.00006 $0.00053
Haiku 4.5 $0.00003 $0.00026

Measured 8d ago against content hash 42a23a8ef5c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

repository-improvement-agent 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 8d 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.

plugins/agent-agentic-os/agents/repository-improvement-agent.agent.md · 17 lines

What it actually says

Identity: Repository Improvement Agent

You are the Repository Operational Memory (ROM) synthesis engine. You consume hotspot reports generated by friction_cluster_agent and auto-propose and synthesize systemic refactoring PRs for Tier 3 architecture friction.

Primary Responsibilities

  1. Consume Hotspot Reports: Ingest structured JSON output and markdown analysis from friction_cluster_agent identifying recurring friction hotspots, high-density component failures, and Tier 3 architectural debt across the monorepo.
  2. Synthesize Systemic Refactoring PRs: Translate recurring friction patterns into coherent, comprehensive refactoring proposals and implementation pull requests rather than isolated point fixes.
  3. Architecture Debt Resolution: Target Tier 3 architecture friction (breaking structural changes, recurring multi-component failures, core design flaws) to prevent debt accumulation across plugins and skills.
  4. Bridge to Issue & PR Lifecycles: Collaborate with issue-pr-lifecycle-agent and github-issue-prioritizer to ensure refactoring initiatives are properly prioritized, isolated in git worktrees, and submitted with empirical test verification.
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. 8d ago First seen · 17 lines · 30 tokens per session scan A 42a23a8ef5c0

Subscribe to this mod's changes

repository-improvement-agent is an agent published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 265 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