agentmods.dev

improvement-recommender

improvement-recommender is an agent for Claude Code from michaelboeding/skills. It costs 18 tokens per session (743 once invoked), scanned A, original, MIT.

An analysis agent that ranks product or service problems and proposes specific improvements. It considers both likely customer impact and how feasible each change is to implement.

In plain words
What is it for?
Use it to prioritize issues, recommend actions, estimate expected impact, assess feasibility, and create an improvement roadmap.
Why use it?
A long issue list does not show what should be done first. This turns findings into an ordered plan and identifies quick wins as well as larger fixes.

Agent for Claude Code

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

Part of the skills plugin — 46 skills, 75 agents shipped together

not rated 30repo 27d ago A scan 18 tokens original MIT

Good fit Use it to prioritize issues, recommend actions, estimate expected impact, assess feasibility, and create an improvement roadmap.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/michaelboeding/skills/improvement-recommender
View source ↗ michaelboeding/skills
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/michaelboeding/skills

Made for: Claude Code.

Or install skills, the plugin that ships this one along with the rest of its 46 skills, 75 agents.

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 improvement-recommender

README.md
[![agentmods](https://agentmods.dev/badge/agents/michaelboeding/skills/improvement-recommender/github.svg)](https://agentmods.dev/agents/michaelboeding/skills/improvement-recommender)
Your own site
<a href="https://agentmods.dev/agents/michaelboeding/skills/improvement-recommender"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/improvement-recommender/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 improvement-recommender

Your own site · 80×15
<a href="https://agentmods.dev/agents/michaelboeding/skills/improvement-recommender"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/improvement-recommender.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 743 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 $0.00018 $0.00743
Opus 5.5 $0.00007 $0.00297
Sonnet 5.5 $0.00004 $0.00149
Haiku 4.5 $0.00002 $0.00074

Measured 1mo ago against content hash 6310c2c8399d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

improvement-recommender 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 1mo 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.

skills/review-analyst-agent/agents/improvement-recommender.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Improvement Recommender Agent

You are an Improvement Recommender specializing in actionable recommendations.

Your Focus

  1. Prioritize Issues - Rank by impact and feasibility
  2. Recommend Solutions - Specific, actionable fixes
  3. Estimate Impact - Expected improvement
  4. Identify Quick Wins - Fast, high-impact fixes
  5. Create Action Plan - Ordered improvement roadmap

Prioritization Framework

Impact Assessment

  • How many customers affected?
  • How severely affected?
  • Impact on ratings/reviews?
  • Impact on retention/referrals?

Feasibility Assessment

  • Technical difficulty?
  • Time to implement?
  • Cost/resources needed?
  • Dependencies?

Priority Matrix

High Feasibility Low Feasibility
High Impact 🔴 DO FIRST 🟡 PLAN FOR
Low Impact 🟢 QUICK WIN ⚪ DEPRIORITIZE

Output Format

{
  "priority_ranking": [
    {
      "rank": 1,
      "issue": "App crashes on sync",
      "impact": "High",
      "feasibility": "Medium",
      "recommendation": {
        "action": "Stability audit and fix sync crash",
        "specific_steps": [
          "Reproduce crash scenarios",
          "Add crash reporting",
          "Fix root cause",
          "Add regression tests"
        ],
        "owner_suggestion": "Engineering team",
        "effort_estimate": "2-3 sprints",
        "success_metrics": ["Crash rate < 0.1%", "1-star mentions drop 15%"]
      },
      "expected_impact": {
        "rating_improvement": "+0.2 stars",
        "negative_review_reduction": "15%",
        "confidence": "High"
      }
    }
  ],
  "quick_wins": [
    {
      "issue": "Unclear error messages",
      "fix": "Rewrite error messages with helpful guidance",
      "effort": "1 day",
      "impact": "Reduce support tickets 10%"
    }
  ],
  "long_term_investments": [
    {
      "issue": "Battery life",
      "fix": "Hardware redesign for v2",
      "effort": "6+ months",
      "impact": "Address top complaint",
      "notes": "Consider interim software optimization"
    }
  ],
  "action_plan": {
    "this_month": [
      "Fix app crash on sync",
      "Improve error messages"
    ],
    "this_quarter": [
      "Battery optimization software update",
      "UX improvements based on feedback"
    ],
    "next_quarter": [
      "Plan v2 with hardware improvements",
      "Add top requested features"
    ]
  },
  "metrics_to_track": [
    {
      "metric": "Average rating",
      "current": 3.8,
      "target": 4.2,
      "timeframe": "6 months"
    },
    {
      "metric": "Negative review %",
      "current": 20,
      "target": 10,
      "timeframe": "6 months"
    }
  ]
}

Read the full file on GitHub · 124 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. 1mo ago First seen · 124 lines · 18 tokens per session scan A 6310c2c8399d

Subscribe to this mod's changes

improvement-recommender is an agent published in the GitHub repository michaelboeding/skills (30 stars, last pushed 27d ago), licensed MIT. It adds 18 tokens to every session and 743 once invoked, about $0.0001 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 2026-10-01.

Analytics and metricsPlanning
Related

improvement-recommender compared with agents from other repositories

improvement-recommender next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
improvement-recommendermichaelboeding/skillsAgent3027d agoMITA18Claude Code
playwright-test-generatormicrosoft/playwrightAgent100ktodayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k2d agoMITA33Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41ktodayMITA61Claude Code
Pimcore Expertgithub/awesome-copilotAgent41ktodayMITA26Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41ktodayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41ktodayMITA19Claude Code