sumitake · sumitake · Jul 30, 2026 · Jul 30, 2026 · Jul 30, 2026 · Jul 30, 2026
@@ -9,7 +9,7 @@
   "plugins": [],
   "metadata": {
     "description": "Agent collaboration plugin marketplace",
-    "version": "4.5.4",
+    "version": "4.6.0",
     "repository": "https://github.com/sumitake/agent-collab"
   }
 }
@@ -10,7 +10,7 @@
     {
       "name": "agent-collab",
       "description": "Unified dynamic-host collaboration package. Centralized skills and async coordination work without legacy packages; every model-execution route requires the verified signed plugin artifact.",
-      "version": "4.5.4",
+      "version": "4.6.0",
       "author": {
         "name": "John Osumi"
       },
@@ -32,7 +32,7 @@
   ],
   "metadata": {
     "description": "Agent collaboration plugin marketplace",
-    "version": "4.5.4",
+    "version": "4.6.0",
     "repository": "https://github.com/sumitake/agent-collab"
   }
 }
@@ -13,7 +13,16 @@ Describe the user-visible outcome and why it belongs in the public policy/client
 - [ ] Skill specs and generated `SKILL.md` files are in parity.
 - [ ] Claude and Codex marketplaces/manifests are in parity.
 - [ ] A unique `changelog.d/` fragment is present for a user-visible change; generated `CHANGELOG.md` changes only in a release/bootstrap PR.
-- [ ] Version metadata is bumped when behavior or distributed content changes.
+- [ ] Version metadata is bumped when behavior or distributed content changes. Every surface has to move together or `check_release_consistency.py` reports drift, so bump all seven:
+  1. `plugins/agent-collab/.claude-plugin/plugin.json`
+  2. `plugins/agent-collab/.codex-plugin/plugin.json`
+  3. `.claude-plugin/marketplace.base.json` → then re-run `python3 scripts/build_marketplace.py`
+  4. root `README.md` — the summary-table row **and** the `## What's new - vX.Y.Z` heading (two separate edits)
+  5. `plugins/agent-collab/README.md` — `Current: **X.Y.Z**` **and** the "this same X.Y.Z package" line
+  6. `scripts/skill-build-config.json` — the **nested** `skill_version` inside the package block, not a new top-level key → then re-run `python3 scripts/build_skills.py`, which rewrites every generated `SKILL.md`
+  7. a `changelog.d/` fragment naming `agent-collab X.Y.Z`
+
+  The generated `CHANGELOG.md` is **not** one of them — at PR time the version requirement is met by that fragment, so a content PR can bump without touching a release-only file. Run `python3 scripts/check_release_consistency.py` and the test suite; between them they name any surface you missed.
 
 ## Verification
 

@@ -78,7 +78,7 @@ trust:
   primary's identity, model, and session dynamically — no per-host forks to
   drift out of sync.
 
-This public repository distributes that one package, **agent-collab** (v4.5.4), and is
+This public repository distributes that one package, **agent-collab** (v4.6.0), and is
 the source of truth for the coordinator policy, skills, migration tooling, the
 fail-closed runtime client, contribution governance, and release-safety checks.
 The signed and notarized darwin-arm64 native runtime is committed in this
@@ -129,7 +129,26 @@ Contributors need no access to the private build/sign system. See
 
 | Package | Version | Role |
 |---|---:|---|
-| `agent-collab` | 4.5.4 | Unified skills, dynamic host policy, migration preflight, and verified native-runtime client |
+| `agent-collab` | 4.6.0 | Unified skills, dynamic host policy, migration preflight, and verified native-runtime client |
+
+## What's new - v4.6.0
+
+- **A Claude Code host observes its own active model.** Claude Code does not
+  export the model to the environment, so a Claude host resolved
+  `active_model='unknown'` and was the only host family that could never reach
+  a governance-ready identity; every governance route failed closed with
+  `unknown_family`. The model is now observed from the live session's own
+  transcript, mirroring the existing Codex rollout contract: strict
+  lowercase-UUID session key before any path join, the same ownership,
+  symlink, hardlink and permission predicates, post-open `fstat`
+  re-validation, a bounded tail read, and strict JSON decoding.
+  `CLAUDE_CONFIG_DIR` is honoured, so a relocated installation resolves too.
+  Model validation is by shape rather than a pinned list, so future models
+  resolve with no code change. Identity on a Claude host is observation-only:
+  every field is recorded non-empty, so configuration cannot fill an
+  unobserved session into governance eligibility, and a model that is not
+  anthropic-shaped fails closed rather than reassigning the host-derived
+  family.
 
 ## What's new - v4.5.4
 

@@ -0,0 +1,5 @@
+### Changed
+
+- Stamp agent-collab 4.6.0. The user-visible change in this version is the Claude-host active-model observation from #77: a Claude Code host resolves its active model from the live session transcript, so it can reach a governance-ready identity like the other host families instead of always resolving `unknown`. That change altered distributed content and should have carried the bump at the time; it did not, because the bump was mistakenly believed to require editing the generated `CHANGELOG.md`, which is reserved to release PRs.
+
+- Spell out in the pull-request template all seven surfaces a version bump has to move: both plugin manifests, `.claude-plugin/marketplace.base.json` (plus the `build_marketplace.py` regeneration), the root README summary row and its whatsnew heading, the package README's `Current:` and package lines, the nested `skill_version` in `scripts/skill-build-config.json` (plus the `build_skills.py` regeneration that restamps all 47 generated `SKILL.md` files), and a `changelog.d/` fragment naming the version. The generated `CHANGELOG.md` is not among them, because at PR time the requirement is met by that fragment. Missing several of these is what produced the false conclusion that a content PR could not bump at all.
@@ -1,6 +1,6 @@
 {
   "name": "agent-collab",
-  "version": "4.5.4",
+  "version": "4.6.0",
   "description": "Unified dynamic-host collaboration package with centralized skills, migration preflight, and a verified plugin-relative native runtime boundary. The signed runtime artifact is intentionally absent until the private build/sign integration completes.",
   "author": {
     "name": "John Osumi"

@@ -1,6 +1,6 @@
 {
   "name": "agent-collab",
-  "version": "4.5.4",
+  "version": "4.6.0",
   "description": "Unified dynamic-host collaboration package with centralized skills, migration preflight, and a verified plugin-relative native runtime boundary. The signed runtime artifact is intentionally absent until the private build/sign integration completes.",
   "author": {
     "name": "John Osumi"

@@ -7,7 +7,7 @@ verifiable compliance evidence, and operator final-say, delivered as one
 package for every supported host. This document is the package's technical
 reference; the repository README carries the purpose and governance narrative.
 
-Current: **4.5.4**
+Current: **4.6.0**
 
 It resolves `primary_id`, `primary_family`, `active_model`, `host_runtime`, and
 `session_identifier` from the current host or explicit configuration. On a
@@ -69,7 +69,7 @@ one macOS `LC_BUILD_VERSION` with minimum macOS 14.0 instead of trusting those
 manifest labels. The broker transport and provider protocol are both version 2.
 The package
 carries both `.claude-plugin/plugin.json` and `.codex-plugin/plugin.json`; both
-identify this same 4.5.4 package.
+identify this same 4.6.0 package.
 
 Codex, Gemini, OpenCode, Grok, and Composer are broker-only contracts. Their sealed requests cross a
 mode-`0600`, digest-bound per-user launchd Unix socket; launchd starts the exact

@@ -1,6 +1,6 @@
 ---
 name: agent-readiness
-version: 4.5.4
+version: 4.6.0
 description: Evaluate whether an agent, model, CLI, plugin, or role is ready for a proposed responsibility. Use when the user says "agent readiness," "is this agent ready," "can Codex be primary," "can Grok handle this role," "promote this agent," "evaluate this worker," "review model readiness," or "/agent-collab:agent-readiness." Also offer this proactively before assigning a new primary, reviewer, worker, delegate, headless, release, or merge-related role to Claude, Codex, Antigravity/Gemini, Grok, or a future agent.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: agent-runtime-status
-version: 4.5.4
+version: 4.6.0
 defaults:
   tier: Fast
   effort: low

@@ -1,6 +1,6 @@
 ---
 name: ai-writing-auditor
-version: 4.5.4
+version: 4.6.0
 description: Audits prose for the tells of machine-generated writing and rewrites it to read as if a careful human wrote it, without softening the actual content. Use when the user says "de-AI this text", "audit this writing for AI patterns", "make this read human", or "/agent-collab:ai-writing-auditor." Also offer this proactively when a piece of customer-facing or published prose is dense with the stock phrasing and mechanical structure typical of unedited model output.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: architect
-version: 4.5.4
+version: 4.6.0
 description: Request read-only architecture consultation for codebase analysis, system design, implementation planning, decomposition, or long-horizon coding strategy. Use when the user says "ask the architect," "have Grok design this," "architecture consultation," "plan this implementation," "decompose this build," "analyze the system design," or "/agent-collab:architect." Also offer this proactively before a substantial multi-system or long-horizon implementation where an independent architecture pass can reduce rework. This role never edits files, runs shell commands or tests, mutates a worktree, opens PRs, merges, or deploys.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: autonomy-readiness
-version: 4.5.4
+version: 4.6.0
 description: Evaluate whether an autonomous, always-on, scheduled, headless, or self-evolving workflow is ready to run safely. Use when the user says "autonomy readiness," "activation gate review," "is this workflow ready to run autonomously," "go/no-go autonomy," "always-on readiness," "headless operation review," or "/agent-collab:autonomy-readiness." Also offer this proactively before enabling background agents, recurring automations, auto-merge/self-evolution, external actions, unattended host runs, or any workflow that can continue without a human watching.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: brainstorm
-version: 4.5.4
+version: 4.6.0
 defaults:
   tier: Fast
   effort: low

@@ -1,6 +1,6 @@
 ---
 name: chain-configurator
-version: 4.5.4
+version: 4.6.0
 defaults:
   tier: Standard
   effort: medium

@@ -1,6 +1,6 @@
 ---
 name: chain
-version: 4.5.4
+version: 4.6.0
 defaults:
   tier: Standard
   effort: medium

@@ -1,6 +1,6 @@
 ---
 name: code-review
-version: 4.5.4
+version: 4.6.0
 defaults:
   tier: Advanced
   effort: high

@@ -1,6 +1,6 @@
 ---
 name: compose-skills
-version: 4.5.4
+version: 4.6.0
 description: Select a bounded, token-aware combination of collaboration skills or task lenses before execution. Use when the user says "compose skills," "which skills should I use," "use skill composition," "select a recipe," "combine these skills," or "/agent-collab:compose-skills." Also offer this proactively when a task plausibly needs multiple lenses, reviewers, or agents and would benefit from progressive disclosure, explicit fan-out limits, and a smallest-useful-skill plan before routing or loading full skill bodies.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: data-engineer
-version: 4.5.4
+version: 4.6.0
 description: Builds and hardens the pipelines and warehouse structures that move data from source systems to the people and systems that consume it. Use when the user says "build the ETL pipeline", "design the dbt models", "orchestrate this pipeline", or "design the warehouse schema", or "/agent-collab:data-engineer." Also offer this proactively when a pipeline lacks idempotency, has no data-quality checks, or moves data through undocumented schema contracts.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: debate
-version: 4.5.4
+version: 4.6.0
 defaults:
   tier: Advanced
   effort: high

@@ -1,6 +1,6 @@
 ---
 name: delegate
-version: 4.5.4
+version: 4.6.0
 defaults:
   tier: Fast
   effort: low

@@ -1,6 +1,6 @@
 ---
 name: dev-delegate
-version: 4.5.4
+version: 4.6.0
 defaults:
   tier: Standard
   effort: medium

@@ -1,6 +1,6 @@
 ---
 name: elixir-engineer
-version: 4.5.4
+version: 4.6.0
 description: Senior Elixir and OTP engineer for fault-tolerant, concurrent, and Phoenix-based systems. Use when the user says "review this supervision tree", "why did this GenServer crash", "help me design this OTP process architecture", or "/agent-collab:elixir-engineer." Also offer this proactively when a change adds a new process, alters a restart strategy, or touches a Phoenix channel or LiveView boundary.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: eval-engineer
-version: 4.5.4
+version: 4.6.0
 description: Designs evaluation suites and scoring methods that measure whether an AI-backed workflow is actually good enough to ship. Use when the user says "design evals for this", "build an eval suite", "how should we measure this workflow", or "/agent-collab:eval-engineer." Also offer this proactively when a project ships a prompt, retrieval pipeline, or agent workflow with no structured way to tell whether a change made it better or worse.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: go-engineer
-version: 4.5.4
+version: 4.6.0
 description: Senior Go engineer for concurrent, service-oriented, and cloud-native code. Use when the user says "review this Go service for concurrency bugs", "help me design this Go interface", "why is this goroutine leaking", or "/agent-collab:go-engineer." Also offer this proactively when a change adds a goroutine, channel, or context-cancellation path without an obvious termination guarantee.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: governance-review
-version: 4.5.4
+version: 4.6.0
 description: Use when the operator says "governance review," "high-stakes review," "tiebreaker," or "second opinion." Also offer this proactively when reviewer-family independence must be enforced.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: hallucination-investigator
-version: 4.5.4
+version: 4.6.0
 description: Traces a specific wrong or fabricated AI output back to its root cause in context, retrieval, prompting, or tool use, and recommends the most targeted fix. Use when the user says "why is it hallucinating", "investigate this fabrication", "trace this wrong answer", or "/agent-collab:hallucination-investigator." Also offer this proactively when a factuality failure has been reported but no one has yet reconstructed why the system produced that specific wrong answer.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: incident-responder
-version: 4.5.4
+version: 4.6.0
 description: Leads live incident response — triage, containment, evidence-driven root-cause analysis, and postmortem writeups for active outages or breaches. Use when the user says "we have an incident", "production is down", or "run the postmortem for this outage", or "/agent-collab:incident-responder." Also offer this proactively when the user is trying to write the incident timeline or communicate status while a service disruption is still unresolved.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: intent-check
-version: 4.5.4
+version: 4.6.0
 defaults:
   tier: Fast
   effort: low

@@ -1,6 +1,6 @@
 ---
 name: knowledge-compile
-version: 4.5.4
+version: 4.6.0
 description: Compile multiple sources into a durable, cited knowledge dossier without mixing claims, assumptions, and decisions. Use when the user says "compile knowledge," "build a dossier," "create a knowledge base," "synthesize these sources," "preserve research context," "make this reviewable later," or "/agent-collab:knowledge-compile." Also offer this proactively when a task spans several repos, PRs, papers, articles, logs, agent messages, or drafts and future agents need source-separated context for independent review.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: kubernetes-specialist
-version: 4.5.4
+version: 4.6.0
 description: Designs, hardens, and troubleshoots Kubernetes clusters and the workloads running on them. Use when the user says "review this Kubernetes manifest", "why is my pod crash-looping", or "help me design a multi-tenant cluster", or "/agent-collab:kubernetes-specialist." Also offer this proactively when a change touches Deployment/StatefulSet/DaemonSet specs, RBAC bindings, network policies, or persistent volume claims.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: llm-architect
-version: 4.5.4
+version: 4.6.0
 description: Designs the structural shape of an LLM-powered system — how context is assembled, how tools and retrieval are wired in, and how output flows to the caller. Use when the user says "design the RAG pipeline", "plan the agent architecture", or "help me structure the prompt pipeline", or "/agent-collab:llm-architect." Also offer this proactively when a project is wiring multiple prompts, tools, and retrieval steps together without a clear contract between them.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: logic-check
-version: 4.5.4
+version: 4.6.0
 defaults:
   tier: Advanced
   effort: xhigh

@@ -1,6 +1,6 @@
 ---
 name: long-context
-version: 4.5.4
+version: 4.6.0
 defaults:
   tier: Advanced
   effort: high

@@ -1,6 +1,6 @@
 ---
 name: merge-resolve
-version: 4.5.4
+version: 4.6.0
 defaults:
   tier: Advanced
   effort: high

@@ -1,6 +1,6 @@
 ---
 name: migration-doctor
-version: 4.5.4
+version: 4.6.0
 description: Use when the user says "migration doctor," "check old collaboration plugins," "verify agent-collab migration," or "/agent-collab:migration-doctor." Also offer this proactively after installing or updating agent-collab, when provider routing is blocked, or when a retired package may still be selected from an installed plugin or cache.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: mlops-engineer
-version: 4.5.4
+version: 4.6.0
 description: Designs and hardens the infrastructure that carries models from training through production serving. Use when the user says "set up a model registry", "build the training pipeline", "deploy this model to production", or "/agent-collab:mlops-engineer." Also offer this proactively when a project trains or serves models but has no versioned artifacts, no promotion gate, or no monitoring for prediction quality.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: orchestrate
-version: 4.5.4
+version: 4.6.0
 defaults:
   tier: Standard
   effort: medium

@@ -1,6 +1,6 @@
 ---
 name: postgres-engineer
-version: 4.5.4
+version: 4.6.0
 description: Administers and hardens PostgreSQL at the engine level — configuration, replication, vacuum behavior, and locking under real workloads. Use when the user says "tune postgres for this workload", "design a vacuum strategy", "set up replication", or "fix our connection pooling", or "/agent-collab:postgres-engineer." Also offer this proactively when a PostgreSQL deployment shows replication lag, bloat, connection exhaustion, or a failover plan that has never been tested.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: prompt-regression-tester
-version: 4.5.4
+version: 4.6.0
 description: Builds and runs comparison suites that catch behavioral drift when a prompt, model, or workflow configuration changes. Use when the user says "did the prompt change regress anything", "compare these prompt versions", "regression-test this prompt change", or "/agent-collab:prompt-regression-tester." Also offer this proactively when someone is about to swap a prompt, model, or tool wiring in a live workflow without a way to check whether existing behavior held.
 ---
 

@@ -1,6 +1,6 @@
 ---
 name: qa-verify
-version: 4.5.4
+version: 4.6.0
 defaults:
   tier: Fast
   effort: low

@@ -1,6 +1,6 @@
 ---
 name: red-team
-version: 4.5.4
+version: 4.6.0
 defaults:
   tier: Advanced
   effort: high