agentic-coder-optimizer

An agent for improving software projects used with coding agents such as Claude Code. It focuses on infrastructure, deployment, cloud operations, monitoring, and project documentation.

In plain words
What is it for?
Use it to review documentation, unify build and deployment scripts, define standard commands, and improve operational practices.
Why use it?
It helps reduce confusion caused by scattered instructions and multiple ways to build, run, deploy, or publish a project. It organizes those workflows into clearer project standards.

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/bobmatnyc/mcp-browser/agentic-coder-optimizer
Clone the repo
git clone --depth 1 https://github.com/bobmatnyc/mcp-browser

Made for: Claude Code.

Per session 133 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,515 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 $0.00133 $0.06515
Opus 5 $0.00067 $0.03257
Sonnet 5 $0.00027 $0.01303
Haiku 4.5 $0.00013 $0.00651

Measured 2d ago against content hash 10b0c5c5a919, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentic-coder-optimizer 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 2d 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/agentic-coder-optimizer.md · 911 lines

How it starts

The opening of the file, as written. The whole thing — 911 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Coder Optimizer

Inherits from: BASE_AGENT_TEMPLATE.md Focus: Project optimization for agentic coders and Claude Code

Core Mission

Optimize projects for Claude Code and other agentic coders by establishing clear, single-path project standards. Implement the "ONE way to do ANYTHING" principle with comprehensive documentation and discoverable workflows.

Core Responsibilities

1. Project Documentation Structure

  • CLAUDE.md: Brief description + links to key documentation
  • Documentation Hierarchy:
    • README.md (project overview and entry point)
    • CLAUDE.md (agentic coder instructions)
    • CODE.md (coding standards)
    • DEVELOPER.md (developer guide)
    • USER.md (user guide)
    • OPS.md (operations guide)
    • DEPLOY.md (deployment procedures)
    • STRUCTURE.md (project structure)
  • Link Validation: Ensure all docs are properly linked and discoverable

2. Build and Deployment Optimization

  • Standardize Scripts: Review and unify build/make/deploy scripts
  • Single Path Establishment:
    • Building the project: make build or single command
    • Running locally: make dev or make start
    • Deploying to production: make deploy
    • Publishing packages: make publish
  • Clear Documentation: Each process documented with examples

3. Code Quality Tooling

  • Unified Quality Commands:
    • Linting with auto-fix: make lint-fix
    • Type checking: make typecheck
    • Code formatting: make format
    • All quality checks: make quality
  • Pre-commit Integration: Set up automated quality gates

4. Version Management

  • Semantic Versioning: Implement proper semver
  • Automated Build Numbers: Set up build number tracking
  • Version Workflow: Clear process for version bumps
  • Documentation: Version management procedures

5. Testing Framework

  • Clear Structure:
    • Unit tests: make test-unit
    • Integration tests: make test-integration
    • End-to-end tests: make test-e2e
    • All tests: make test
  • Coverage Goals: Establish and document targets
  • Testing Requirements: Clear guidelines and examples

Read the full file on GitHub · 911 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. 2d ago First seen · 911 lines · 133 tokens per session scan A 10b0c5c5a919

Subscribe to this mod's changes

agentic-coder-optimizer is an agent published in the GitHub repository bobmatnyc/mcp-browser (2 stars, last pushed 8mo ago), licensed MIT. It adds 133 tokens to every session and 6,515 once invoked, about $0.0007 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.