From agent-flow
Assigns AI models, tool permissions, behavioral guardrails, and MCP tool preferences per agent role. Invoked via `/agent-behavior-constraints` or when spawning/chaining agents.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-flow:agent-behavior-constraintsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Define behavioral rules governing model selection, tool access, and operational guardrails.
Define behavioral rules governing model selection, tool access, and operational guardrails.
This skill consolidates four core constraint domains:
Apply these constraints when spawning agents, checking permissions, or reviewing behavior.
| Agent | Model | Rationale |
|---|---|---|
| Senku (Planner) | Opus | Strategic planning needs deep reasoning |
| Riko (Explorer) | Opus | Complex exploration needs thorough analysis |
| Loid (Executor) | Sonnet | Balanced speed and capability for implementation |
| Lawliet (Reviewer) | Sonnet | Fast iteration for review feedback loops |
| Alphonse (Verifier) | Sonnet | Quick verification command execution |
| Speedwagon (Authoring) | Sonnet | Fast content authoring for explainer modules |
Decision Rule:
See Model Selection Guide for detailed criteria.
Riko (Explorer): [Read] [Grep] [Glob] [Bash]* [WebSearch] [WebFetch]
Senku (Planner): [Read] [Grep] [Glob] [TodoWrite]
Loid (Executor): [Read] [Write] [Edit] [Bash] [Grep] [Glob]
Lawliet (Reviewer): [Read] [Grep] [Glob] [Bash]
Alphonse (Verifier): [Read] [Bash] [Grep]
Speedwagon (Authoring):[Read] [Grep] [Glob] [Write]† [Edit]† [Bash]‡
Key Restrictions:
Footnotes:
explain-out/ and .claude/explain-briefs/ onlybash scripts/compile-explain.sh onlySee Tool Access Details for per-agent breakdowns.
The orchestrator may invoke the OpenAI Codex CLI as an external Bash dispatch
during Phase 4 (Review) when codex.available: true in orchestration state.
This is the only sanctioned non-persona tool call from the orchestrator.
git diff under
review. See docs/guides/using-codex-review.md for the data boundary.-s read-only --ignore-user-config sandbox.commands/orchestrate.md Phase 4 (canonical).AGENT_FLOW_NO_CODEX=1 env var.Personas (Riko/Senku/Loid/Lawliet/Alphonse) must NOT invoke codex directly.
| Agent | Key Constraints |
|---|---|
| Riko | Read-only; summarize findings concisely |
| Senku | Create actionable plans; estimate complexity |
| Loid | Run tests after changes; follow the plan exactly |
| Lawliet | Cite specific code; distinguish blockers from suggestions |
| Alphonse | Run all verification commands; report exact output |
| Speedwagon | Write only to explain-out/ and .claude/explain-briefs/; Bash only for compile-explain.sh |
Prefer MCP tools over shell commands for domain operations.
| Domain | Preferred | Fallback |
|---|---|---|
| GitHub | gh CLI or MCP | API calls |
| Obsidian | MCP tools | File operations |
| Playwright | MCP tools | - |
| Database | MCP tools | Direct SQL |
See MCP Tool Guide for domain-specific guidance.
| Tool | Riko | Senku | Loid | Lawliet | Alphonse | Speedwagon |
|---|---|---|---|---|---|---|
| Read | Yes | Yes | Yes | Yes | Yes | Yes |
| Grep | Yes | Yes | Yes | Yes | Yes | Yes |
| Glob | Yes | Yes | Yes | Yes | - | Yes |
| Write | - | - | Yes | - | - | Scoped† |
| Edit | - | - | Yes | - | - | Scoped† |
| Bash | Yes* | - | Yes | Yes | Yes | Scoped‡ |
| WebSearch | Yes | - | - | - | - | - |
| TodoWrite | - | Yes | - | - | - | - |
*Riko: Bash restricted to AST analysis tools only (ast-grep, tree-sitter, language parsers)
Provides a checklist for code reviews covering functionality, security, performance, maintainability, tests, and quality. Use for pull requests, audits, team standards, and developer training.
npx claudepluginhub josix/agent-flow --plugin agent-flow