Lesson 4 of 6 · 0%Distinguish tools, skills, plugins, and authorityNext
Course map

Foundations and Architecture

0 of 6 complete0 of 6

Lesson 4.1 · 35 minutes

Distinguish tools, skills, plugins, and authority

Give an agent only the capability and instructions it needs, then identify the policy and runtime conditions that still limit its actions.

Skip course map
Current lessonDistinguish tools, skills, plugins, and authority0% complete · 0/6 lessons

Foundations and Architecture

0% complete · Current: Distinguish tools, skills, plugins, and authority

Verifiedon 2026.7.1-2

Action boundary

Before you act

Expected result
A workflow proposal names the action, required tool, instruction source, plugin dependency if any, data scope, approval condition, and kill switch.
Failure mode
A skill instruction is treated as enforcement, or a plugin install is treated as permission for every agent and sender to use its capability.
Rollback
Do not install or enable the proposed capability. Remove the draft proposal and return to a read-only synthetic example.

Capability is not one thing

A tool is a typed action an agent can call. A skill is an instruction pack that teaches a repeatable workflow. A plugin adds runtime surfaces such as tools, providers, channels, hooks, or packaged skills. These categories answer different questions:

Question Correct surface
Can the agent perform an action? Tool, subject to policy and runtime conditions
Does the agent know the approved workflow? Skill
Does the runtime need a new integration? Plugin

A model receives only tools that survive the active profile, allow/deny policy, provider restrictions, sandbox state, channel permissions, and plugin availability. That means “the plugin is installed” is not a sufficient approval record.

Lab: turn a vague request into a capability contract

Start with: “Let the support agent check an order status.” Rewrite it into seven fields: source of request; read-only data needed; exact tool; approved skill or procedure; identity allowed to invoke it; redaction rule; and a disable condition. Do not use a real order system. A mock JSON response is enough to test the design.

The correct contract should say what cannot happen too: no refunds, no recipient changes, no filesystem or shell access, and no reuse of a support lookup as authority to message a customer.

Checkpoint

An agent has a polished skill that says “ask before sending.” Does that protect against a misconfigured message tool? No. Instructions influence behaviour; tool policy and approvals control capability. Conversely, a visible tool does not make a workflow safe unless its input scope, requester, output route, and rollback are defined.

Source provenanceVerification and sources

Review receipt rr_foundations_capability_boundaries

Outcome
approved
Method
source-review
Reviewer
forge-independent-review
Reviewed

Evidence

Limitations

  • Primary-source editorial review; no plugin or tool policy was enabled.

Open the public evidence snapshot

Lesson checkpoint

Ready to move on?

Mark this lesson complete when you can apply its outcome without relying on the examples above.