@ikon85/agent-workflow-kit 0.44.1 → 0.45.0

package/.agents/skills/audit-skills/SKILL.md

@@ -122,10 +122,13 @@ otherwise stay invisible.
 
 ### 2. Audit in parallel — one subagent per skill
 
-Before dispatch, resolve a provider-neutral Routing intent through
-`src/lib/routeDispatcher.mjs` and require a Dispatch receipt from the shared
-spawn guard. A detected transport is not authorization; AFK dispatch stops
-unless requested/applied route, model/effort enforcement, environment
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
 precedence, and catalog/access/policy revisions are proved.
 
 Run **one read-only research subagent per skill** — several in parallel in a

package/.agents/skills/code-review/SKILL.md

@@ -81,10 +81,13 @@ When `projectEnrichment` is active, read `docs/agents/code-review.md` first. App
 
 ## Execution
 
-Before dispatch, resolve a provider-neutral Routing intent through
-`src/lib/routeDispatcher.mjs` and require a Dispatch receipt from the shared
-spawn guard. A detected transport is not authorization; AFK dispatch stops
-unless requested/applied route, model/effort enforcement, environment
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
 precedence, and catalog/access/policy revisions are proved.
 
 - Run both axes as **parallel sub-agents** — separate context each, so neither poisons the other's read. Give the Standards sub-agent the Standards sources **plus** the full Fowler baseline in its prompt; it has no other way to see the baseline.

package/.agents/skills/codebase-design/DESIGN-IT-TWICE.md

@@ -18,10 +18,13 @@ Show this to the user, then immediately proceed to Step 2. The user reads and th
 
 ### 2. Spawn sub-agents
 
-Before dispatch, resolve a provider-neutral Routing intent through
-`src/lib/routeDispatcher.mjs` and require a Dispatch receipt from the shared
-spawn guard. A detected transport is not authorization; AFK dispatch stops
-unless requested/applied route, model/effort enforcement, environment
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
 precedence, and catalog/access/policy revisions are proved.
 
 <!-- mirror-xform:start codex-parallel-subagent-dispatch -->

package/.agents/skills/improve-codebase-architecture/INTERFACE-DESIGN.md

@@ -18,10 +18,13 @@ Show this to the user, then immediately proceed to Step 2. The user reads and th
 
 ### 2. Spawn sub-agents
 
-Before dispatch, resolve a provider-neutral Routing intent through
-`src/lib/routeDispatcher.mjs` and require a Dispatch receipt from the shared
-spawn guard. A detected transport is not authorization; AFK dispatch stops
-unless requested/applied route, model/effort enforcement, environment
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
 precedence, and catalog/access/policy revisions are proved.
 
 <!-- mirror-xform:start codex-parallel-subagent-dispatch -->

package/.agents/skills/improve-codebase-architecture/SKILL.md

@@ -43,10 +43,13 @@ This skill is _informed_ by the project's domain model. The domain language give
 
 Read the project's domain glossary and any ADRs in the area you're touching first.
 
-Before dispatch, resolve a provider-neutral Routing intent through
-`src/lib/routeDispatcher.mjs` and require a Dispatch receipt from the shared
-spawn guard. A detected transport is not authorization; AFK dispatch stops
-unless requested/applied route, model/effort enforcement, environment
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
 precedence, and catalog/access/policy revisions are proved.
 
 <!-- mirror-xform:start codex-explorer-dispatch -->

package/.agents/skills/orchestrate-wave/SKILL.md

@@ -109,7 +109,7 @@ node scripts/readiness.mjs check --skill orchestrate-wave --json
 Pass only host-supplied inventory through `capabilityAdapter.claude` or `.codex`,
 then call the selector. It returns exactly one target; missing or `unknown` evidence
 degrades A → B → C. A model claim is not evidence; do not emulate a missing primitive.
-Before any spawn, resolve the provider-neutral Routing intent through the shared resolver and spawn guard, then use the active Claude or Codex adapter. Codex contributes only its dated host attestation through `routingAdapters/codex.mjs`; it does not create a second catalog, Access graph, or Routing policy. A detected transport is not authorization. The Dispatch receipt must show requested and applied route, model/effort enforcement, environment precedence on mismatch, and catalog/access/policy revisions. AFK blocks unverified, unauthorized, overridden, unenforced, or silently degraded routes; a Codex host without model and effort selectors blocks differentiated AFK before spawn, and unreachable routes follow policy handoff/inherit/block exactly.
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent block first, otherwise the workflow classifier — and authorize the whole run once through a Dispatch plan whose hash binds every unit, intent, route and reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a Dispatch receipt from the shared spawn guard that carries the authorization id the plan recorded. A detected transport is not authorization; AFK dispatch stops unless requested/applied route, model/effort enforcement, environment precedence, and catalog/access/policy revisions are proved. Before any spawn, resolve the provider-neutral Routing intent through the shared resolver and spawn guard, then use the active Claude or Codex adapter. Codex contributes only its dated host attestation through `routingAdapters/codex.mjs`; it does not create a second catalog, Access graph, or Routing policy. A detected transport is not authorization. The Dispatch receipt must show requested and applied route, model/effort enforcement, environment precedence on mismatch, and catalog/access/policy revisions. AFK blocks unverified, unauthorized, overridden, unenforced, or silently degraded routes; a Codex host without model and effort selectors blocks differentiated AFK before spawn, and unreachable routes follow policy handoff/inherit/block exactly.
 - **Path A:** requires the literal `Workflow` tool, callable and permitted, plus
   individually proven named phases, run identity, runtime output validation,
   journal, and resume. Then read [its recipe](references/dispatch-workflow.md).

package/.agents/skills/orchestrate-wave/references/dispatch-subagents.md

@@ -54,6 +54,15 @@ Reconciliation is never delegated to a subagent.
 
 ## Round 2 — Build
 
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
+precedence, and catalog/access/policy revisions are proved.
+
 For the current reconciled batch, spawn **one builder per slice**, again as one
 concurrent batch joined by an explicit wait. Give each builder the verbatim
 builder contract, its reconciled allowlist, and its required commands. Resolve

package/.agents/skills/orchestrate-wave/references/dispatch-workflow.md

@@ -48,6 +48,15 @@ current reconciled batch, make one `agent()` call per slice with explicit
 the reconciled allowlist and required commands in each verbatim builder prompt;
 the main thread still performs `semanticVerify` on every returned report.
 
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
+precedence, and catalog/access/policy revisions are proved.
+
 Before each `agent()` call, resolve its provider-neutral Routing intent and pass
 the decision through the shared spawn guard and active surface adapter. The
 Claude adapter must attest Workflow model/effort precedence in the current

package/.agents/skills/research/SKILL.md

@@ -11,10 +11,13 @@ Before applying this Core skill, run `node scripts/project-skill-extension.mjs i
 Project extensions may specialize Project details, but cannot weaken Core user gates, safety, ownership, or validation. A contradiction blocks and requires an Explicit fork.
 <!-- project-extension:protocol-v1:end -->
 
-Before dispatch, resolve a provider-neutral Routing intent through
-`src/lib/routeDispatcher.mjs` and require a Dispatch receipt from the shared
-spawn guard. A detected transport is not authorization; AFK dispatch stops
-unless requested/applied route, model/effort enforcement, environment
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
 precedence, and catalog/access/policy revisions are proved.
 
 Spin up a **background agent** to do the research, so you keep working while it reads.

package/.agents/skills/to-issues/SKILL.md

@@ -436,6 +436,20 @@ Reference the blocking ticket(s), or "None - can start immediately".
 **Decision:** <chosen option + why it wins on the criteria that matter + what was consciously traded off>
 **Verdict sink:** <ADR / this body / follow-up slice #N>
 
+## Routing intent
+<!-- Provider-neutral and durable: the dimensions of the WORK, never a model,
+     effort, or provider name. Written as ONE blank-line-delimited block so the
+     dispatching surface can read it as the explicit intent instead of guessing
+     from workflow signals; a second such block in the body makes it ambiguous
+     and unreadable. Keys and vocabularies are owned by the intent schema. -->
+intent-version: 2
+routing-intent: <judgment | development | mechanical>
+reasoning-intent: <deep | balanced | light>
+task-shape: <single-step | multi-step | long-horizon>
+risk: <low | moderate | high>
+autonomy-requirement: <supervised | afk>
+context-need: <focused | repository | long-context>
+
 ## Handoff Start Command
 <!-- SELF-CONTAINED: scope + live-verify live HERE, never as a "see anchor
      handoff" pointer — the anchor carries no per-slice handoff blocks anymore, and a
@@ -444,7 +458,7 @@ Reference the blocking ticket(s), or "None - can start immediately".
 ```
 Welle <N> · Slice <X> (<closes #x | refs #<prd#>, Parent #<prd#>>). Read #<prd#> for decisions.
 Start skill: 🧭 Design Grill → /grill-with-docs · 🔬 Verify Spike → /verify-spike · 📐 Trade-off/Research → /decision-gate · AFK → /implement · HITL → /grill-me → /implement.
-Routing intent: `routing-intent: <judgment | development | mechanical>` · `reasoning-intent: <deep | balanced | light>`. The dispatching surface resolves the current executable route; never persist that provider route here.
+Routing intent: the body's `## Routing intent` block — read it as the explicit intent. The dispatching surface resolves the current executable route from it; never persist that provider route here.
 Worktree: your project's worktree helper, or `git worktree add`
 Scope (<N> files) — REQUIRED FIELD, blast-radius estimate at cut time; the build session checks it against its own recon findings, >2x deviation → STOP:
 - <concrete file + change>
@@ -453,10 +467,17 @@ PR: <closes #x | Part of #<prd#> — NEVER closes on the anchor>.
 ```
 <!-- mirror-xform:end -->
 
+Every published issue carries that block, gate slices included — an unstated
+intent forces the dispatching surface to classify from workflow signals, and a
+guess is what the block exists to replace. Fill each dimension from the slice
+itself: `autonomy-requirement: afk` only for the AFK bucket (§5c), `supervised`
+for every HITL slice.
+
 At execution time, consume that provider-neutral intent only through
-`src/lib/routeDispatcher.mjs` and its shared spawn guard. The active Claude or
-Codex adapter must produce Dispatch receipt v2 with requested/applied route,
-model/effort enforcement, precedence, and catalog/access/policy revisions
+`src/lib/routeDispatcher.mjs` and its shared spawn guard, under the Dispatch
+plan that authorized the run. The active Claude or Codex adapter must produce
+Dispatch receipt v2 with requested/applied route, model/effort enforcement,
+precedence, the plan's authorization id, and catalog/access/policy revisions
 before an AFK subagent starts; the durable issue never claims that proof.
 </issue-template>
 

package/.claude/skills/audit-skills/SKILL.md

@@ -122,10 +122,13 @@ otherwise stay invisible.
 
 ### 2. Audit in parallel — one subagent per skill
 
-Before dispatch, resolve a provider-neutral Routing intent through
-`src/lib/routeDispatcher.mjs` and require a Dispatch receipt from the shared
-spawn guard. A detected transport is not authorization; AFK dispatch stops
-unless requested/applied route, model/effort enforcement, environment
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
 precedence, and catalog/access/policy revisions are proved.
 
 Run **one read-only research subagent per skill** — several in parallel in a

package/.claude/skills/code-review/SKILL.md

@@ -81,10 +81,13 @@ When `projectEnrichment` is active, read `docs/agents/code-review.md` first. App
 
 ## Execution
 
-Before dispatch, resolve a provider-neutral Routing intent through
-`src/lib/routeDispatcher.mjs` and require a Dispatch receipt from the shared
-spawn guard. A detected transport is not authorization; AFK dispatch stops
-unless requested/applied route, model/effort enforcement, environment
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
 precedence, and catalog/access/policy revisions are proved.
 
 - Run both axes as **parallel sub-agents** — separate context each, so neither poisons the other's read. Give the Standards sub-agent the Standards sources **plus** the full Fowler baseline in its prompt; it has no other way to see the baseline.

package/.claude/skills/codebase-design/DESIGN-IT-TWICE.md

@@ -18,10 +18,13 @@ Show this to the user, then immediately proceed to Step 2. The user reads and th
 
 ### 2. Spawn sub-agents
 
-Before dispatch, resolve a provider-neutral Routing intent through
-`src/lib/routeDispatcher.mjs` and require a Dispatch receipt from the shared
-spawn guard. A detected transport is not authorization; AFK dispatch stops
-unless requested/applied route, model/effort enforcement, environment
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
 precedence, and catalog/access/policy revisions are proved.
 
 <!-- mirror-xform:start codex-parallel-subagent-dispatch -->

package/.claude/skills/codex-build/SKILL.md

@@ -21,6 +21,19 @@ The role-flip of `/codex-review`: there, Claude builds the plan and Codex critiq
 
 ## Prerequisites (verify once, fast)
 
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
+precedence, and catalog/access/policy revisions are proved.
+
+`scripts/codex-exec.sh` is the transport that decision names, never a
+second router: the wrapper applies the resolved pair and its rollout file
+is the readback the receipt quotes. Echoing a config default is not proof.
+
 - Let `scripts/codex-exec.sh` preflight Codex before launch. It enforces the
   exact tested-version allowlist, authentication, platform, and capabilities;
   surface any failure rather than retrying silently.

package/.claude/skills/codex-review/SKILL.md

@@ -19,6 +19,19 @@ This is a **deliberate, high-stakes tool** — reach for it on auth, data models
 
 ## Prerequisites (verify once, fast)
 
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
+precedence, and catalog/access/policy revisions are proved.
+
+`scripts/codex-exec.sh` is the transport that decision names, never a
+second router: the wrapper applies the resolved pair and its rollout file
+is the readback the receipt quotes. Echoing a config default is not proof.
+
 - Let `scripts/codex-exec.sh` preflight Codex before launch. It enforces the
   exact tested-version allowlist, authentication, platform, and capabilities;
   surface any failure to the user rather than retrying silently.

package/.claude/skills/grill-me-codex/SKILL.md

@@ -86,6 +86,20 @@ Act 1 (grill) complete — plan locked with the user. MAX_ROUNDS=<n>.
 Now hand the locked plan to Codex for adversarial review. Same engine, mechanics verified end-to-end (2026-06-04).
 
 ### Prerequisites (verify once, fast)
+
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
+precedence, and catalog/access/policy revisions are proved.
+
+`scripts/codex-exec.sh` is the transport that decision names, never a
+second router: the wrapper applies the resolved pair and its rollout file
+is the readback the receipt quotes. Echoing a config default is not proof.
+
 - Let `scripts/codex-exec.sh` preflight Codex before launch. It enforces the
   exact tested-version allowlist, authentication, platform, and capabilities;
   surface any failure rather than retrying silently.

package/.claude/skills/grill-with-docs-codex/SKILL.md

@@ -170,6 +170,20 @@ Act 1 (grill-with-docs) complete — plan locked, CONTEXT.md/ADRs updated. MAX_R
 Hand the locked plan to Codex for adversarial review. Mechanics verified end-to-end (2026-06-04).
 
 ### Prerequisites
+
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
+precedence, and catalog/access/policy revisions are proved.
+
+`scripts/codex-exec.sh` is the transport that decision names, never a
+second router: the wrapper applies the resolved pair and its rollout file
+is the readback the receipt quotes. Echoing a config default is not proof.
+
 - Let `scripts/codex-exec.sh` preflight Codex before launch. It enforces the
   exact tested-version allowlist, authentication, platform, and capabilities;
   surface any failure rather than retrying silently.

package/.claude/skills/improve-codebase-architecture/INTERFACE-DESIGN.md

@@ -18,10 +18,13 @@ Show this to the user, then immediately proceed to Step 2. The user reads and th
 
 ### 2. Spawn sub-agents
 
-Before dispatch, resolve a provider-neutral Routing intent through
-`src/lib/routeDispatcher.mjs` and require a Dispatch receipt from the shared
-spawn guard. A detected transport is not authorization; AFK dispatch stops
-unless requested/applied route, model/effort enforcement, environment
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
 precedence, and catalog/access/policy revisions are proved.
 
 <!-- mirror-xform:start codex-parallel-subagent-dispatch -->

package/.claude/skills/improve-codebase-architecture/SKILL.md

@@ -43,10 +43,13 @@ This skill is _informed_ by the project's domain model. The domain language give
 
 Read the project's domain glossary and any ADRs in the area you're touching first.
 
-Before dispatch, resolve a provider-neutral Routing intent through
-`src/lib/routeDispatcher.mjs` and require a Dispatch receipt from the shared
-spawn guard. A detected transport is not authorization; AFK dispatch stops
-unless requested/applied route, model/effort enforcement, environment
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
 precedence, and catalog/access/policy revisions are proved.
 
 <!-- mirror-xform:start codex-explorer-dispatch -->

package/.claude/skills/orchestrate-wave/SKILL.md

@@ -109,7 +109,7 @@ node scripts/readiness.mjs check --skill orchestrate-wave --json
 Pass only host-supplied inventory through `capabilityAdapter.claude` or `.codex`,
 then call the selector. It returns exactly one target; missing or `unknown` evidence
 degrades A → B → C. A model claim is not evidence; do not emulate a missing primitive.
-Before any spawn, resolve the provider-neutral Routing intent through the shared resolver and spawn guard, then use the active Claude or Codex adapter. Codex contributes only its dated host attestation through `routingAdapters/codex.mjs`; it does not create a second catalog, Access graph, or Routing policy. A detected transport is not authorization. The Dispatch receipt must show requested and applied route, model/effort enforcement, environment precedence on mismatch, and catalog/access/policy revisions. AFK blocks unverified, unauthorized, overridden, unenforced, or silently degraded routes; a Codex host without model and effort selectors blocks differentiated AFK before spawn, and unreachable routes follow policy handoff/inherit/block exactly.
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent block first, otherwise the workflow classifier — and authorize the whole run once through a Dispatch plan whose hash binds every unit, intent, route and reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a Dispatch receipt from the shared spawn guard that carries the authorization id the plan recorded. A detected transport is not authorization; AFK dispatch stops unless requested/applied route, model/effort enforcement, environment precedence, and catalog/access/policy revisions are proved. Before any spawn, resolve the provider-neutral Routing intent through the shared resolver and spawn guard, then use the active Claude or Codex adapter. Codex contributes only its dated host attestation through `routingAdapters/codex.mjs`; it does not create a second catalog, Access graph, or Routing policy. A detected transport is not authorization. The Dispatch receipt must show requested and applied route, model/effort enforcement, environment precedence on mismatch, and catalog/access/policy revisions. AFK blocks unverified, unauthorized, overridden, unenforced, or silently degraded routes; a Codex host without model and effort selectors blocks differentiated AFK before spawn, and unreachable routes follow policy handoff/inherit/block exactly.
 - **Path A:** requires the literal `Workflow` tool, callable and permitted, plus
   individually proven named phases, run identity, runtime output validation,
   journal, and resume. Then read [its recipe](references/dispatch-workflow.md).

package/.claude/skills/orchestrate-wave/references/dispatch-subagents.md

@@ -54,6 +54,15 @@ Reconciliation is never delegated to a subagent.
 
 ## Round 2 — Build
 
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
+precedence, and catalog/access/policy revisions are proved.
+
 For the current reconciled batch, spawn **one builder per slice**, again as one
 concurrent batch joined by an explicit wait. Give each builder the verbatim
 builder contract, its reconciled allowlist, and its required commands. Resolve

package/.claude/skills/orchestrate-wave/references/dispatch-workflow.md

@@ -48,6 +48,15 @@ current reconciled batch, make one `agent()` call per slice with explicit
 the reconciled allowlist and required commands in each verbatim builder prompt;
 the main thread still performs `semanticVerify` on every returned report.
 
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
+precedence, and catalog/access/policy revisions are proved.
+
 Before each `agent()` call, resolve its provider-neutral Routing intent and pass
 the decision through the shared spawn guard and active surface adapter. The
 Claude adapter must attest Workflow model/effort precedence in the current

package/.claude/skills/research/SKILL.md

@@ -11,10 +11,13 @@ Before applying this Core skill, run `node scripts/project-skill-extension.mjs i
 Project extensions may specialize Project details, but cannot weaken Core user gates, safety, ownership, or validation. A contradiction blocks and requires an Explicit fork.
 <!-- project-extension:protocol-v1:end -->
 
-Before dispatch, resolve a provider-neutral Routing intent through
-`src/lib/routeDispatcher.mjs` and require a Dispatch receipt from the shared
-spawn guard. A detected transport is not authorization; AFK dispatch stops
-unless requested/applied route, model/effort enforcement, environment
+Before dispatch, resolve a provider-neutral Routing intent — an explicit intent
+block first, otherwise the workflow classifier — and authorize the whole run
+once through a Dispatch plan whose hash binds every unit, intent, route and
+reason. Dispatch only through `src/lib/routeDispatcher.mjs`, and require a
+Dispatch receipt from the shared spawn guard that carries the authorization id
+the plan recorded. A detected transport is not authorization; AFK dispatch
+stops unless requested/applied route, model/effort enforcement, environment
 precedence, and catalog/access/policy revisions are proved.
 
 Spin up a **background agent** to do the research, so you keep working while it reads.