The Handbook's Vocabulary, A to Z
The handbook’s vocabulary in one lookup table, A to Z: the objects, the artifacts, the mechanisms, the roles, and the named constructs, each defined in one to three sentences with a link to its canonical home. The entries are written to be quoted. The canonical homes carry the argument.
OAuth, WIMSE, and OpenID, Mapped to the Architecture
The Mission is the architecture’s new primitive. The rest should compose. This appendix tests that claim against the ratified OAuth substrate, the complete active OAuth and WIMSE working-group queues, selected individual drafts, and the relevant OpenID Foundation specifications. It separates publication status from architectural relationship and states the important deltas and substitution hazards plainly.
Six Questions for Anyone Claiming Agent Authorization
When a vendor says they support agent authorization, ask six questions: what is the approved task object, what derives authority from it, what keeps authority strictly narrower as work fans out, what checks each action at the moment of use, what happens when it is revoked, and can an auditor pull one identifier and see the whole task. The test is intentionally unforgiving: no approved task object means no category claim, token validation is not runtime enforcement, token expiry is not revocation, and logs are not task evidence. A vendor that passes can write the honest deployment claim with level, enforcement scope, freshness, evidence, and exclusions.
Answers for the People Who Run Today's Control Planes
A skeptical FAQ for IAM practitioners and architects. Twenty-three objections test mission-based authorization against IdPs, workload identity, OAuth, RAR and UMA, short-lived tokens, PDPs and Zero Trust, Shared Signals, PAM and IGA, workflow engines, internal composition, open-world discovery, semantic misuse, enforcement bypass, lifecycle ownership, and privacy. The answers concede where existing systems are sufficient, identify where a Mission-shaped implementation may already exist under another name, and limit the standards case to the boundaries where private task state no longer reaches.
The Q3 Board Packet, Exhibit by Exhibit
The handbook argues the architecture. This appendix shows the bytes: a Mission Intent submitted through PAR, the approved record’s integrity anchors, a Mission-bound access token, an AuthZEN permit bound to parameters, a parameter_violation denial, the revocation that ends the task, the lifecycle event that announces it, and the status check that fails the 02:00 resume. Every exhibit follows the current editor’s copies, and the two integrity anchors reproduce byte for byte.
The Category, the Litmus Test, the Landscape, and the Running Example
Mission-based authorization governs the approved task, not just the credential, session, or request. This page is the field reference: the definition and litmus test for what counts as mission-based, a competitive landscape, the adoption stages, threats and non-goals, the canonical diagram and glossary, and the Q3 board-packet example threaded through the handbook.
Token-Side and Resource-Side Authorization Are Two Projections of One Approved Task
The least-privilege MCP series ends on a gap: token-side and resource-side authorization both work per call, and neither names the task the user approved. This essay applies Mission-Bound Authorization at the MCP boundary. The Mission is the durable approved task, tokens and PDP decisions are projections of it, tool discovery and invocation and approval line up against it, expansion routes through a fresh approval, and audit joins on one identifier. A denial is traced end to end to show the whole spine working.
A History of Delegated Authority, from Passwords to Missions
Authorization looks the way it does because each generation solved the question its era made urgent, and deferred one question that someone else was always carrying: what approved work is this, and is it still on? Purpose was not absent. A second stack of tickets, purchase orders, workflows, and approval systems held it locally, and people carried it between systems. UMA decoupled protected-resource access from synchronous resource-owner interaction, and workload identity made software actors attributable without making their credentials task-specific. What never became a standard cross-boundary object was the approved undertaking itself, with authority derived from it and a lifecycle independent of any credential. Usage control identified ongoing authorization two decades ago. Unattended work now removes the human carrier and makes shared task state an operational requirement. This is the history that makes the Mission a legible next step rather than an idea from nowhere.
The Outside Evidence, the Named Bets, and the Handbook's Close
The handbook closes on judgment. First the strongest outside evidence: AAuth, the proposed clean-slate agent protocol, adopted a first-class mission layer in its 01 revision after this model’s AAuth mapping circulated: not independent replication, adoption by a designer free to say no, which is its own kind of proof. Then the honest bets: admission grain, issuer home, the price of Termination, the necessity of the object itself, the portability of its authority, and the classification line, each stated with the evidence that would falsify it. The laws and the claim gate are the invariants. The bets are the wagers, and deployment experience, not this handbook, will settle them.
Where the Layer Sits in the Estate
Issuance gating and runtime enforcement are two independent chokepoints, strictly stronger together: a gap in PEP coverage is still bounded at the token layer, and an outstanding token is still stopped at the action layer. The Mission Authority Server, the issuance grant, the Mandate, and Cross-Domain Projection extend the pattern space. And the structural reading that platform engineers reach for unprompted: the layer is the control plane for delegated authority, mapped concept by concept from desired state to the fleet API, with the disciplines that keep the framing honest.
The Substrate-Neutral Model and Its Verb Spine
OAuth is the flagship binding because it is deployment reality, but the model does not depend on it. This part states the framework the profiles realize: four functions (compilation, projection, containment, continuity), a verb spine of ten verbs from propose to analyze, and the fundamental-versus-accidental test. Which ideas survive if OAuth disappears? Nearly all of them: the layer, the laws, the vocabulary, the approved task with an integrity-anchored record, approval evidence, runtime containment. What is accidental is the realization: PAR, RAR, the claim names, the wire shapes.
The OAuth Community's Gap Catalog, Answered Line by Line
The standards community is converging on a problem statement: agents break OAuth’s pre-approval paradigm, tokens cannot represent delegation chains, revocation cannot reach a task, and consent screens cannot survive a thousand scopes. The agent authorization use-case catalog names nine scenarios and rolls its analysis up to five major gaps, and this part answers the catalog line by line at both grains with machinery that existed before it was published: task-level revocation is the Mission kill switch, bulk revocation is Mission Management, multi-hop chains are act chains and Child Missions, scope explosion dies at Mission-grain consent, and the paradigm mismatch is the discovery loop. One answer is partial and one is delegated, and the tally is stated rather than smoothed.
What NIST AI RMF, the EU AI Act, and ISO/IEC 42001 Ask Agents to Prove
The third kind of outside framing is the one with auditors behind it. NIST AI RMF, the EU AI Act, and ISO/IEC 42001 converge on one demand: show me. Show me who is accountable, what the system is for, how you observe it, and how you stop it. In most agent stacks the honest answer is archaeology through session logs. In this architecture the artifact that enforces is the artifact that documents: the Mission is the documented purpose, the approval is the accountable decision, the evidence family is the log, and Termination is the interrupt. The crosswalk maps eight obligations onto machinery that exists for safety reasons, and then names what compliance still requires, because evidence is not certification.
Fifteen Agentic Threats and the LLM Top 10, Each Given a Verdict
Security reviewers do not arrive with your framing. They arrive with OWASP’s: fifteen agentic threats from memory poisoning to human manipulation, plus the LLM Top 10. This part crosswalks both onto the handbook and refuses the move that makes crosswalks worthless, claiming everything. Each threat gets one of three verdicts. Contained means the threat lands on machinery built for it, with a draft behind it. Bounded means the cause is out of authorization’s reach but the blast radius is capped at the action gate. Delegated means it is not an authorization problem and a named complement owns it. Six of the fifteen are contained, nine are bounded, and half the LLM Top 10 is honestly someone else’s layer.
A Critical Crosswalk from Patrick Parker's Seven Laws to Mission-Bound Authorization
Patrick Parker’s Seven Laws of AIdentity describe the dynamics a system must govern when agents act through delegated authority: split actors, generated intent, bounded agency, continuous authorization, least exposure, justifiable action chains, and proof-carrying action. This part maps those laws onto Mission-Bound Authorization without turning resemblance into compliance. The strongest matches are generated intent and bounded agency. Continuous authorization and split-actor attribution require the runtime and identity profiles. Least exposure, chain necessity, policy retention, evidence completeness, and embodied action remain conditional or outside the current wire model.
How Mission-Bound Authorization Contains the Defining Agent Threat Model
Simon Willison named the combination that makes agents dangerous: access to private data, exposure to untrusted content, and the ability to communicate externally, held together in one loop. Any two legs are safe. All three are an exfiltration machine waiting for a poisoned document. This part runs the handbook against that threat model: the three legs become separately typed action classes under one Mission, the external leg becomes a consequential action that needs a fresh parameter-bound permit, mediated custody keeps the egress credential out of the agent’s hands, and the harness downgrades egress once untrusted content enters the session. Then the honest residuals: enforcement scope, composition, and the semantic gap.
Sessions Are Not Authority, Safe Unwinding, and Tamper-Evident Evidence
The first five layers make the Mission approvable, enforceable, governable, and delegable. This operational close makes them hold up against a real agent: a harness that treats session continuity as recoverable state and not as authority, an orchestrator that unwinds work already in flight when a Mission stops, and a transparency profile that makes the suite’s evidence independently verifiable across trust domains. It closes with a synthesis of the six operational layers and the Mission Assurance Levels, the practice-side view of the adoption path the architecture chapter stages.
Observe, Revoke, Grow, Complete
The issuance core gives a Mission three states and gates derivation on active. This part adds the surfaces that make state actionable over time: Status for canonical pull freshness with Signals as its push complement, Expansion for governed growth, and Completion for monotonic narrowing. One rule threads through all four. Only active permits reliance, so every state a newer profile adds fails safe for a consumer that predates it.
From Mission-Bound Tokens to Mission-Bound Actions
OAuth issuance bounds what authority may exist. It does not check the action at the point of use, so an active Mission becomes ambient authority within a token’s lifetime. The runtime layer closes that gap. A PEP at each consequential execution boundary obtains a permit from a PDP that evaluates the action, its parameters, the actor, and the current Mission state before any consequential effect occurs. The runtime profile fixes the invariants. The AuthZEN profile is its concrete wire binding.
From Authenticated Agent Identity to Bounded, Narrowing Authority
The AI agent auth best practices give an agent workload identity, credentials, and delegated user authority. This part binds Mission authority to that identity. The mission claim projects the approved task into every derived token, attested instance identifiers and actor chains keep every actor attributable, and delegated work gets explicit, narrower, separately revocable authority. A sub-agent that acts because it descends from a parent session is inheriting ambient authority, not delegated authority. Child Missions give durable sub-agents their own revocable handles with strict-subset authority and cascade revocation. Offline attenuation, the experimental roadmap for fan-out at scale, keeps the Authorization Server off the hot path with the runtime state check as the surviving kill switch.
Shaping, Consent Evidence, and Deferred Approval with Revision
A user request is untrusted input. This part covers the integrity of the approval event, the layer before any token exists: the client-side shaper that proposes a candidate Mission Intent, the Consent Evidence that commits the structured consent disclosure the Authorization Server recorded as rendered (not the pixels or the Approver’s comprehension), and the deferred and revisable approval that lets a human reviewer narrow a proposal in place. Authority is created only when the Authorization Server validates, narrows, and approves.
Crawl, Walk, Run
A definitive architecture that ends without a build order is a tour, not a blueprint. Most estates start at the read-only ceiling: agents capped at read access, humans approving or executing the writes, and pilots that never graduate. This closer names what that posture costs and stages the way off it: crawl by shipping the issuance core (approved, integrity-anchored Missions and a possession-independent kill switch, honestly labeled governance rather than safety), walk by adding the Runtime-Enforced level (per-action enforcement, the AuthZEN binding, and Status freshness, all on substrate that already shipped), and run by climbing to the Governed and High-Assurance Agent levels, each of which makes a broader class of write authority defensible. Plus the ecosystem to compose with, the five operational surfaces you will own, and the pieces the community still has to standardize.
The Missing Object Above Tokens and Sessions
The AI agent auth best-practices draft names the Mission and declares its translation into authorization out of scope. This is the core argument on the other side of that line: why the approved task is the missing object above authentication and instance identity, how the argument converged, the Mission-versus-Intent boundary, and where to start. The definitions, object model, lifecycle, and glossary live in the Reference.
Translating the Corporate-Card Model into Mission-Bound Authorization
What the Corporate Card Already Solved walked a working delegated-authority architecture one control at a time and never mentioned a protocol. This part is the joint between that mental model and this chapter’s architecture. The five rules the card world taught become the five laws of delegated authority, stated for any substrate. The corporate-card test becomes the claim gate a vendor claim must pass. And the build lists that closed each card post, the things the agent stack cannot borrow from the expense world, turn out to enumerate the draft family: disclosure integrity, field-speed narrowing, checkpoints per boundary, endings that propagate, and a record that earns trust without a bank.