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.
npx agentmods add agents/bobmatnyc/mcp-browser/agentic-coder-optimizergit clone --depth 1 https://github.com/bobmatnyc/mcp-browserWhat 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.
| Model | Per session | Once 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 |
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.
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 buildor single command - Running locally:
make devormake start - Deploying to production:
make deploy - Publishing packages:
make publish
- Building the project:
- 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
- Linting with auto-fix:
- 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
- Unit tests:
- Coverage Goals: Establish and document targets
- Testing Requirements: Clear guidelines and examples
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.
- 2d ago First seen · 911 lines · 133 tokens per session scan A 10b0c5c5a919
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.