diff --git a/agents/README.md b/agents/README.md index 3ddc540..576e428 100644 --- a/agents/README.md +++ b/agents/README.md @@ -7,27 +7,29 @@ This directory contains specialized AI agent profiles. Each profile defines a ro | Agent | File | Model | Use When | | -------------------- | ------------------------- | ------ | -------------------------------------------------------- | | Planner | `planner.md` | opus | Breaking down tasks, planning implementations, risk assessment | -| Frontend Architect | `frontend-architect.md` | opus | UI components, performance, accessibility, React/Next.js | -| Backend Architect | `backend-architect.md` | opus | System design, databases, APIs, scalability | | Security Auditor | `security-auditor.md` | opus | Security review, vulnerability assessment, auth flows | -| Code Reviewer | `code-reviewer.md` | sonnet | Code quality, PR review, best practices | +| Code Reviewer | `code-reviewer.md` | opus | Code quality, PR review, deep analysis | +| Frontend Architect | `frontend-architect.md` | sonnet | UI components, performance, accessibility, React/Next.js | +| Backend Architect | `backend-architect.md` | sonnet | System design, databases, APIs, scalability | | Test Engineer | `test-engineer.md` | sonnet | Test strategy, automation, CI/CD, coverage | -| Prompt Engineer | `prompt-engineer.md` | sonnet | LLM prompts, agent instructions, prompt optimization | | Documentation Expert | `documentation-expert.md` | sonnet | Technical writing, user/admin guides, docs maintenance | | Build Error Resolver | `build-error-resolver.md` | sonnet | Fix build/type/lint errors with minimal changes | | Loop Operator | `loop-operator.md` | sonnet | Monitor autonomous loops, detect stalls, escalate | +| Prompt Engineer * | `prompt-engineer.md` | sonnet | LLM prompts, agent instructions (optional, for AI projects) | ## Model Selection -- **opus** — Deep reasoning tasks: planning, architecture, security review. Slower but more thorough. -- **sonnet** — Implementation tasks: code review, testing, writing, fixing. Faster turnaround. +- **opus** — Deep reasoning: planning, security audit, code review. Slower but more thorough. +- **sonnet** — Implementation: architecture execution, testing, writing, fixing. Faster turnaround. + +Principle: planner does the deep thinking, implementation agents execute the plan. ## Tool Restrictions Each agent declares a `tools` array in its frontmatter, following the principle of least privilege: -- **Read-only agents** (planner, architects): Read, Glob, Grep — they advise, not implement -- **Implementation agents** (test-engineer, build-error-resolver): Read, Glob, Grep, Edit, Write, Bash -- **Review agents** (code-reviewer): Read, Glob, Grep, Bash (for git commands) +- **Read-only agents** (planner): Read, Glob, Grep — plans, doesn't implement +- **Implementation agents** (architects, test-engineer, build-error-resolver): Read, Glob, Grep, Edit, Write, Bash +- **Review agents** (code-reviewer, security-auditor): Read, Glob, Grep, Bash (for git/scan commands) ## Agent Selection diff --git a/agents/backend-architect.md b/agents/backend-architect.md index ee4059a..230351a 100644 --- a/agents/backend-architect.md +++ b/agents/backend-architect.md @@ -1,6 +1,6 @@ --- name: backend-architect -model: opus +model: sonnet tools: - Read - Glob diff --git a/agents/code-reviewer.md b/agents/code-reviewer.md index ced2a75..9616c87 100644 --- a/agents/code-reviewer.md +++ b/agents/code-reviewer.md @@ -1,6 +1,6 @@ --- name: code-reviewer -model: sonnet +model: opus tools: - Read - Glob diff --git a/agents/frontend-architect.md b/agents/frontend-architect.md index 0569761..4e8b328 100644 --- a/agents/frontend-architect.md +++ b/agents/frontend-architect.md @@ -1,6 +1,6 @@ --- name: frontend-architect -model: opus +model: sonnet tools: - Read - Glob diff --git a/agents/prompt-engineer.md b/agents/prompt-engineer.md index 805bc7c..7738e9d 100644 --- a/agents/prompt-engineer.md +++ b/agents/prompt-engineer.md @@ -7,8 +7,9 @@ tools: - Grep - Write - Edit +optional: true description: | - Prompt engineering specialist for LLMs. Use when: + Optional agent for projects with LLM integration. Use when: - Creating system prompts for AI agents - Improving existing prompts for better consistency - Debugging prompts that produce inconsistent outputs