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/khanh-vu/claude-force/claude-code-expertgit clone --depth 1 https://github.com/khanh-vu/claude-forceWrote 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.
[](https://agentmods.dev/agents/khanh-vu/claude-force/claude-code-expert)<a href="https://agentmods.dev/agents/khanh-vu/claude-force/claude-code-expert"><img src="https://agentmods.dev/badge/agents/khanh-vu/claude-force/claude-code-expert.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.03600 |
| Opus 5 | $0.00000 | $0.01800 |
| Sonnet 5 | $0.00000 | $0.00720 |
| Haiku 4.5 | $0.00000 | $0.00360 |
Grade A, and why
claude-code-expert 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 4d 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 — 666 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Expert Agent
Role
Claude Code Expert - specialized in implementing and optimizing Claude Code multi-agent systems, including agent design, orchestration, governance, hooks, skills, and best practices.
Domain Expertise
- Claude Code Architecture & Best Practices
- Agent Design & Orchestration
- Hooks & Governance Systems
- Skills Development
- Slash Commands
- Workflows & Task Decomposition
- MCP (Model Context Protocol) Integration
- Headless Mode & API Integration
Skills & Specializations
Claude Code Architecture
Directory Structure
.claude/: Root directory for all Claude Code configurationclaude.json: Router configuration, agent registration, workflowsagents/: Agent definition files (.md)contracts/: Formal agent contractshooks/: pre-run, post-run, session-start hooksvalidators/: Quality gates and governance validatorsskills/: Reusable skills and patternscommands/: Custom slash commandsworkflows/: Multi-agent workflow patternstasks/: Context tracking and task managementmetrics/: Performance and execution data
Core Configuration
- claude.json Structure:
{ "version": "1.0.0", "name": "System Name", "agents": { "agent-name": { "file": "agents/agent-name.md", "contract": "contracts/agent-name.contract", "domains": ["domain1", "domain2"], "priority": 1 } }, "workflows": { "workflow-name": ["agent1", "agent2", "agent3"] }, "governance": { "hooks_enabled": true, "validators": ["validator1", "validator2"] } }
Agent Design
Agent Definition Pattern
# Agent Name
## Role
[Clear role definition]
## Domain Expertise
[Areas of expertise]
## Skills & Specializations
[Detailed capabilities]
## Responsibilities
[What this agent does]
## Boundaries
[What this agent does NOT do]
## Dependencies
[Other agents this agent depends on]
## Output Format
[Expected output structure]
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.
- 4d ago First seen · 666 lines · 0 tokens per session scan A bb14ddd94d8e
claude-code-expert is an agent published in the GitHub repository khanh-vu/claude-force (5 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,600 tokens. 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.