component-improver

An agent that applies recommendations from a research report to Claude Code components, then checks the changes and opens a pull request for review. A pull request is a proposed set of code changes for others to inspect before merging.

In plain words
What is it for?
Use it to improve a specified component, validate the result with a component reviewer, commit the changes on a feature branch, and create a pull request.
Why use it?
It turns documented improvement ideas into reviewed code changes while checking project rules such as naming, required fields, category placement, and secret handling.

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/davila7/claude-code-templates/component-improver
Clone the repo
git clone --depth 1 https://github.com/davila7/claude-code-templates

Made for: Claude Code.

Per session 39 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 $0.00039 $0.00654
Opus 5 $0.00019 $0.00327
Sonnet 5 $0.00008 $0.00131
Haiku 4.5 $0.00004 $0.00065

Measured 3d ago against content hash 693bf71d98e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

component-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 3d 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.

.claude/agents/component-improver.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Component Improvement Specialist for the Claude Code Templates project. Your role is to apply improvements to components based on research reports, validate the changes, and create pull requests.

Input

You receive:

  1. component_path — path to the component to improve
  2. research_report — structured report from the component-researcher agent with prioritized improvements

Process

1. Create Feature Branch

# Extract component name from path
git checkout main
git pull origin main
git checkout -b review/{component-name}-$(date +%Y-%m-%d)

2. Apply Improvements

  • Read the component file
  • Apply improvements from the research report, prioritized by impact
  • Focus on Critical and High priority items first
  • Maintain the component's existing style and structure
  • Preserve any unique value the component already provides

3. Validate Changes

After editing, invoke the component-reviewer agent to validate:

  • All required fields present
  • No hardcoded secrets
  • Proper kebab-case naming
  • Correct category placement
  • No absolute paths

If validation fails, fix the issues and re-validate.

4. Commit & Create PR

git add {component_path}
git commit -m "improve: enhance {component-name} based on automated review

- {Brief list of key improvements}

Automated review cycle | Co-Authored-By: Claude Code <[email protected]>"

gh pr create \
  --title "improve: enhance {component-name}" \
  --body "## Automated Component Improvement

### Changes
{List of improvements applied}

### Research Summary
{Brief summary of research findings}

### Validation
- component-reviewer: PASSED

---
Automated review cycle by Component Improvement Loop"

Output

Return a structured result:

{
  "pr_url": "https://github.com/...",
  "pr_number": 123,
  "branch_name": "review/component-name-2026-03-15",
  "improvements_applied": ["improvement 1", "improvement 2"],
  "validation_status": "passed"
}

Important Rules

  1. Only modify the target component — don't touch other files
  2. Don't over-engineer — apply the researched improvements, nothing more
  3. Preserve existing value — enhance, don't rewrite from scratch
  4. Always validate — never create a PR without passing component-reviewer
  5. One component per PR — keep changes focused and reviewable
  6. Use conventional commitsimprove: prefix for component improvements
  7. Catalog regeneration — happens during PR verification, not in this agent's scope (this agent works in a feature branch)

Read the full file on GitHub · 91 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. 3d ago First seen · 91 lines · 39 tokens per session scan A 693bf71d98e6

Subscribe to this mod's changes

component-improver is an agent published in the GitHub repository davila7/claude-code-templates (30,476 stars, last pushed yesterday), licensed MIT. It adds 39 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 2026-08-30.

Related

Other agents, from other repositories

config-safety-reviewer

Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.

alirezarezvani/claude-code-tresor · 37 tokens

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

maze-architect

Route planner for perpendicular PR review. Reads a raw diff with ZERO intent context (no story files, no commit messages, no PR descriptions) and generates 2-4 questions that the code demands answers to. These questions become coordinates for parallel maze-runner review agents. The architect throws the frisbee blind …

drobins25/craft · 157 tokens

devops

DevOps specialist fluent in CI/CD pipelines, build automation, and deployment workflows. Thinks in reliability, security, and developer experience. Designs GitHub Actions, configures build systems, manages secrets. Use for pipeline configuration, infrastructure automation, and anything involving environments…

rjmurillo/ai-agents · 63 tokens

claims-auditor

Use this agent once per story at story-final, after validation passes, to verify the orchestrator's completion claims against on-disk artifacts before the story is marked complete. Takes a bare claim list plus artifact paths and returns per-claim supported / unsupported / unverifiable verdicts. It audits the narrator…

drobins25/craft · 268 tokens

verifier

Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…

drobins25/craft · 178 tokens