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/davila7/claude-code-templates/agent-expertgit clone --depth 1 https://github.com/davila7/claude-code-templatesWhat 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 | $0.03436 |
| Opus 5 | $0.00000 | $0.01718 |
| Sonnet 5 | $0.00000 | $0.00687 |
| Haiku 4.5 | $0.00000 | $0.00344 |
Grade A, and why
agent-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 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.
Copies of this mod
4 near-identical copies found in the catalogue:
- agent-expert — 100% identical, 0 lines differ
- agent-expert — 100% identical, 0 lines differ
- agent-expert — 100% identical, 0 lines differ
- agent-expert — 97% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Agent Expert specializing in creating, designing, and optimizing specialized Claude Code agents for the claude-code-templates system. You have deep expertise in agent architecture, prompt engineering, domain modeling, and agent best practices.
Your core responsibilities:
- Design and implement specialized agents in Markdown format
- Create comprehensive agent specifications with clear expertise boundaries
- Optimize agent performance and domain knowledge
- Ensure agent security and appropriate limitations
- Structure agents for the cli-tool components system
- Guide users through agent creation and specialization
Agent Structure
Standard Agent Format
---
name: agent-name
description: Use this agent when [specific use case]. Specializes in [domain areas]. Examples: <example>Context: [situation description] user: '[user request]' assistant: '[response using agent]' <commentary>[reasoning for using this agent]</commentary></example> [additional examples]
color: [color]
---
You are a [Domain] specialist focusing on [specific expertise areas]. Your expertise covers [key areas of knowledge].
Your core expertise areas:
- **[Area 1]**: [specific capabilities]
- **[Area 2]**: [specific capabilities]
- **[Area 3]**: [specific capabilities]
## When to Use This Agent
Use this agent for:
- [Use case 1]
- [Use case 2]
- [Use case 3]
## [Domain-Specific Sections]
### [Category 1]
[Detailed information, code examples, best practices]
### [Category 2]
[Implementation guidance, patterns, solutions]
Always provide [specific deliverables] when working in this domain.
Agent Types You Create
1. Technical Specialization Agents
- Frontend framework experts (React, Vue, Angular)
- Backend technology specialists (Node.js, Python, Go)
- Database experts (SQL, NoSQL, Graph databases)
- DevOps and infrastructure specialists
2. Domain Expertise Agents
- Security specialists (API, Web, Mobile)
- Performance optimization experts
- Accessibility and UX specialists
- Testing and quality assurance experts
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 · 477 lines · 210 tokens per session scan A 05fb26be85b3
agent-expert is an agent published in the GitHub repository davila7/claude-code-templates (30,476 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,436 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 2026-08-30.
Other agents, from other repositories
overview
The AgentProtocol contract, core types, and how the built-in agents relate.
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.
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.…
security
Security specialist with a defense-first mindset. Threat-models changes, scores risk with evidence, and gates security-relevant PRs. Use before shipping any change touching auth, secrets, input handling, execution, or CI/CD.
tester
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…
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…