agentsop-tool-scoping
Enhancement overlay for multi-agent / tool-using coder agents. Encodes the per-agent tool- scoping discipline that role-based frameworks (CrewAI, LangChain) document only as a passing best-practice: which agent gets which tool, and why blanket-sharing every tool to every agent is a correctness and blast-radius risk. Activates when an agent system has tools AND there is more than one agent (or one agent holding many tools). Treat a tool as a capability grant; scope by least-privilege. ENHANCE overlay — read alongside [[crewai]], [[agentsop-http-tool-wrapping]], [[agentsop-llm-tool-idempotency]]
npx skills add agentsope/SkillAlchemy --skill agentsop-tool-scoping --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Tool Scoping · Per-Agent Tool Binding (Least-Privilege Discipline) > Overlay posture: the base frameworks ([[crewai]], LangChain, LangGraph) all > *define* tools and *bind* them, but treat scoping as a one-line "assign tools > to the agent that needs them" footnote. This overlay makes the rubric > first-class. Non-trivial claims cite inline against > `references/R1-source-evidence.md`. The lever the base skills under-surface: **tool definition and tool binding are two separate decisions.** You define a tool *once* (reusable class/function), but you *bind* it per-agent deliberately. The [[crewai]] SKILL states this in one clause — "tool 定义可复用；但每个 agent 只绑定其角色匹配的工具" `[crewai-sop §DC-3]` — and then moves on. Production failures (wrong-tool selection, an agent running a destructive op outside its role) come from skipping the binding decision and defaulting to "give everyone everything." --- ## 1. 何时激活 (When to Activate) Activate when **any** of these hold: - The system is **multi-agent** (CrewAI crew, LangGraph supervisor/swarm, AutoGen group) AND at least one agent holds ≥1 tool. - A **single agent holds many tools** (rule of thumb: ≥8 — see OP-4) and tool selection has started degr
- 1. 何时激活 (When to Activate)
- 2. 核心心智模型 (Core Mental Model)
- 3. SOP 工作流 (Standard Operating Procedure)
- Phase 0 · Inventory the surface
- Phase 1 · Map roles → minimal tool set
- Phase 2 · Guard side-effectful tools
- Phase 3 · Enforce per-agent tool-count limit
- Phase 4 · Audit
- 4. 操作模型 (Operation Models)
- OP-1 · Least-privilege role→tool mapping
- OP-2 · Side-effect tool guarding
- OP-3 · Shared-registry vs per-agent binding decision
- OP-4 · Per-agent tool-count limit
- OP-5 · Zero-tool synthesis agents
What does the agentsop-tool-scoping skill do?
Enhancement overlay for multi-agent / tool-using coder agents. Encodes the per-agent tool- scoping discipline that role-based frameworks (CrewAI, LangChain) document only as a passing best-practice: which agent gets which tool, and why blanket-sharing every tool to every agent is a correctness and blast-radius risk. Activates when an agent system has tools AND there is more than one agent (or one agent holding many tools). Treat a tool as a capability grant; scope by least-privilege. ENHANCE overlay — read alongside [[crewai]], [[agentsop-http-tool-wrapping]], [[agentsop-llm-tool-idempotency]]
How do I install it?
Run `npx skills add agentsope/SkillAlchemy --skill agentsop-tool-scoping --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From agentsope/SkillAlchemy, a repository with 255 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.