@webpresso/plugin-codex 0.0.15 → 0.0.17

package/skills/fix/SKILL.md

@@ -31,26 +31,26 @@ the blast radius is broader than a local fix.
 
 ## Tooling map
 
-| Need                   | Prefer                                                                      |
-| ---------------------- | --------------------------------------------------------------------------- |
-| Reproduce / large logs | `wp_session_execute`, `wp_session_batch_execute`, `wp_session_execute_file` |
-| Recall prior evidence  | `wp_session_search`, `wp_session_restore`, `wp_session_retrieve`            |
-| Capture decisions      | `wp_session_capture` (do not paste full reports back as user text)          |
-| Scoped proof           | `wp_test`, `wp_lint`, `wp_typecheck`, or `wp_qa`                            |
-| Audits                 | `wp_audit` / `wp_audits`                                                    |
-| Worktree isolation     | `wp_blueprint_put` / `wp_worktree` — never thrash primary checkout          |
-| PR follow-up           | `wp_pr_status`, `wp_pr_upsert` when landing the fix                         |
+| Need                   | Prefer                                                             |
+| ---------------------- | ------------------------------------------------------------------ |
+| Reproduce / large logs | `session_execute`, `session_batch_execute`, `session_execute_file` |
+| Recall prior evidence  | `session_search`, `session_restore`, `session_retrieve`            |
+| Capture decisions      | `session_capture` (do not paste full reports back as user text)    |
+| Scoped proof           | `test`, `lint`, `typecheck`, or `qa`                               |
+| Audits                 | `audit` / `audits`                                                 |
+| Worktree isolation     | `blueprint_put` / `worktree` — never thrash primary checkout       |
+| PR follow-up           | `pr_status`, `pr_upsert` when landing the fix                      |
 
 ## Non-negotiable invariants
 
 1. **Root cause, not symptom.** Trace the failure to the invariant that actually broke. Do not patch callers when the owner is fixable.
 2. **Loud failures, no silent fallbacks.** No default shims, sentinel returns, or catch-and-continue behavior that hides missing config, bad state, or broken boundaries.
-3. **Use the repo's real execution surface.** Prefer MCP `wp_*` tools and repo wrappers over host Bash for search/test/lint. Use bounded session-memory paths for large output.
+3. **Use the repo's real execution surface.** Prefer wp MCP tools and repo wrappers over host Bash for search/test/lint. Use bounded session-memory paths for large output.
 4. **Regression proof is mandatory.** Add or strengthen a test or other reliable proof that would fail against the old behavior.
 5. **Raising timeouts is not a fix.** If a timeout fires, investigate the bottleneck. Only raise a bound when the repo already documents that workload and you can cite measurement.
 6. **Zero suppressions, zero papering over.** No lint disables, ts-ignore, compat aliases, or "temporary" branches to sneak the fix through.
 7. **Minimal correct diff.** Update every consumer of a changed contract in the same change, but do not bundle unrelated cleanup.
-8. **Primary checkout is sacred.** If HEAD is detached, primary is dirty with unrelated work, or you are not on a managed worktree for non-trivial edits → **stop** and move to `wp_worktree` / blueprint owner. Never leave the primary checkout broken.
+8. **Primary checkout is sacred.** If HEAD is detached, primary is dirty with unrelated work, or you are not on a managed worktree for non-trivial edits → **stop** and move to `worktree` / blueprint owner. Never leave the primary checkout broken.
 
 ## Opportunistic fix budget (when called from ultragoal / autopilot)
 
@@ -61,7 +61,7 @@ the blast radius is broader than a local fix.
 - **Tooling / harness findings** ("fix inefficiency you come across", MCP vs shell,
   hook thrash) honor the same budget. Excess → record via the `tech-debt` skill
   (or backlog handoff); do not expand the current epic unbounded.
-- Prefer MCP `wp_*` and session-memory tools over the `wp` CLI / raw shell for
+- Prefer wp MCP tools and session-memory tools over the `wp` CLI / raw shell for
   quality and discovery paths (see tooling map).
 
 ## Protocol
@@ -98,6 +98,19 @@ there, the investigation work is part of `fix`.
 - Read enough surrounding code to say the broken invariant in one sentence.
 - If the issue is nondeterministic, gather evidence until you can describe the slow/flaky/failing case without guessing.
 
+**Prove the mechanism before naming it.** A cause that merely explains the
+symptom is a hypothesis, not a finding. Run the failing thing with the candidate
+values and read what it actually did; trace the claim to the code that executes,
+not the code whose name matches the theory. If you cannot reproduce it, label it
+unverified and keep investigating — do not write it into a plan, commit, or
+report as the cause.
+
+**When a cause is disproved, go back to the command, not to the next story.**
+Substituting another plausible explanation without new observation is how one
+dead route gets three confident, wrong diagnoses. If your second and third
+explanations are still unobserved, you have not reproduced the failure yet.
+Related: `catalog/agent/rules/evidence-discipline.md` § 6.
+
 If the "issue" is actually several unrelated failures, stop and ask which one to fix first.
 
 ### Step 2 — Decide where the fix belongs
@@ -130,10 +143,10 @@ Do not keep production code written before the test as "reference". If you wrote
 
 Run the narrowest checks that prove the repaired behavior on the real repo surface:
 
-- `wp_test` / targeted tests for the repaired path
-- `wp_lint` / `wp_typecheck` for changed surfaces
-- `wp_qa` only when the blast radius needs the bookend
-- Before push: start `wp_ci_preflight`, then poll `wp_ci_preflight_wait` with
+- `test` / targeted tests for the repaired path
+- `lint` / `typecheck` for changed surfaces
+- `qa` only when the blast radius needs the bookend
+- Before push: start `ci_preflight`, then poll `ci_preflight_wait` with
   its run ID until terminal success (use global `wp ci-preflight` only when MCP
   is unavailable). Run it after the final commit and do not edit or commit again
   before pushing: terminal success records the exact-state receipt checked by pre-push.
@@ -141,7 +154,7 @@ Run the narrowest checks that prove the repaired behavior on the real repo surfa
 
 Rules:
 
-- Prefer MCP `wp_*` over raw host Bash.
+- Prefer wp MCP tools over raw host Bash.
 - Reuse fresh logs / session-memory indexed output; do not re-run long commands just to re-read.
 - Read the exit code and summary before making a claim.
 - Never `git push --no-verify` to land an unproven fix.
@@ -158,7 +171,7 @@ cleanup pass, use `ai-deslop` before the final verify handoff.
 
 ### Tool recovery and delivery intent
 
-- Discover the managed owner's current identity with `wp_blueprint_projects`
+- Discover the managed owner's current identity with `blueprint_projects`
   using its absolute `cwd`; pass the returned project ID and matching checkout
   to session tools. A blueprint ID is not a project ID.
 - If quality tooling refuses stale or cross-checkout execution, follow its

package/skills/handoff/SKILL.md

@@ -26,24 +26,24 @@ session. Do **not** paste full transcripts.
 
 ## Tooling map
 
-| Need                   | Prefer                                                                              |
-| ---------------------- | ----------------------------------------------------------------------------------- |
-| Capture decisions      | `wp_session_capture`                                                                |
-| Context-light manifest | `wp_session_context` (required for subagents)                                       |
-| Prior evidence         | `wp_session_search` / `wp_session_retrieve` / `wp_session_restore`                  |
-| Other-host chat        | `wp_conversation_search` / `wp_conversation_get` / `wp_conversation_read` (bounded) |
-| Ultragoal block        | `wp_ultragoal_handoff` (≤40 lines) when a controller is active                      |
+| Need                   | Prefer                                                                     |
+| ---------------------- | -------------------------------------------------------------------------- |
+| Capture decisions      | `session_capture`                                                          |
+| Context-light manifest | `session_context` (required for subagents)                                 |
+| Prior evidence         | `session_search` / `session_retrieve` / `session_restore`                  |
+| Other-host chat        | `conversation_search` / `conversation_get` / `conversation_read` (bounded) |
+| Ultragoal block        | `ultragoal_handoff` (≤40 lines) when a controller is active                |
 
 ## Protocol
 
 1. **State the objective** in one sentence (what the next agent must finish).
-2. **Capture** short pointers via `wp_session_capture`: done, blockers, decisions,
+2. **Capture** short pointers via `session_capture`: done, blockers, decisions,
    evidence refs (log paths, test commands, PR numbers) — not full reports.
-3. **Build** a bounded manifest with `wp_session_context` (objective, constraints,
+3. **Build** a bounded manifest with `session_context` (objective, constraints,
    evidenceRefs, remainingSteps, validation, exclusions). Never copy parent history.
 4. **Optional cross-host:** resolve the conversation with conversation MCP tools;
    read only a **bounded tail** (`maxMessages` / `maxBytes`). Prefer resume
-   commands from `wp_conversation_get` over paste.
+   commands from `conversation_get` over paste.
 5. **Emit ≤40 lines** covering:
    - goal / non-goals
    - done + evidence refs
@@ -63,6 +63,37 @@ session. Do **not** paste full transcripts.
 ## Done looks like
 
 - [ ] ≤40-line handoff with evidence refs
-- [ ] `wp_session_context` (or capture ids) for the next agent
+- [ ] `session_context` (or capture ids) for the next agent
 - [ ] Next skill named
 - [ ] No transcript wall
+
+## Capped or paused host messaging
+
+When the host messaging channel is capped or paused, the ≤40-line manifest IS
+the delivery: the handoff built above carries objective, done, blockers, and
+next steps even if no send lands — emit it once and treat it as sent. Include
+the send-budget state (attempt count, last canary result) in the manifest
+whenever the cap has been in play this session — the count's durable homes
+are the outbox header and the `session_capture` record; re-read both on
+resume. The leader's outbox anchor is durable in two homes: the
+outbox file's own header and a `session_capture` record (`session_capture`
+is registered in `src/mcp/tools/_names.ts`, implemented in
+`src/mcp/tools/session-capture.ts`). When the coordinator incarnation changes,
+re-anchor: write both homes plus the next handoff manifest — a recorded anchor
+goes stale when the identity passes to a new session (observed 2026-10-31: a
+memory-recorded live outbox path no longer existed). On the reader side, a
+stale or dead anchor is not a wall: fall back to the next durable arbitration
+source (`fleet_status` / blueprint task lists) and queues the staleness as
+a blocker in the outbox or manifest; a control send is spent only when the
+channel is open and a reserve slot remains, to surface the staleness. Before executing a resumed
+or queued order, check durable state (the outbox, `fleet_status`,
+blueprint task lists) for a newer arbitration — queued sends deliver late
+and out of order. The manifest carries this check as a required line.
+Queued orders in the manifest are one line each; if the queue would break
+the ≤40-line cap, the manifest carries the count and the outbox path and
+the orders stay in the outbox. Never route around a cap or
+pause: no relays, no peer delegation, no new sessions, no schedulers, no
+filesystem push-delivery to peers, no configuration changes, and no alternate
+transport, tool, or uncapped/legacy send interface. The durable outbox is pull-read
+state, not a route-around. Keep manifests context-light — do not paste full
+transcripts.

package/skills/hooks-doctor/SKILL.md

@@ -7,7 +7,7 @@ scope: repo
 applies_to: [agents]
 related: []
 created: "2026-05-07"
-last_reviewed: "2026-05-07"
+last_reviewed: "2026-11-01"
 name: hooks-doctor
 description: "Hook/plugin doctor for install health. Use for hook blocked, pretooluse, plugin broken."
 argument-hint: "[--skip-mcp]"
@@ -55,13 +55,13 @@ Each check prints `[x]` (pass) or `[ ]` (fail) with a detail line:
 
 ## Failure Remediation
 
-| Check                                            | Likely Cause                                                   | Fix                                                               |
-| ------------------------------------------------ | -------------------------------------------------------------- | ----------------------------------------------------------------- |
-| `pretool-guard` / `post-tool` / etc. — not found | `wp run build` not run after install                           | `wp run build`                                                    |
-| `pretool-guard` / etc. — not executable          | `chmod +x` not persisted                                       | Re-run `wp run prepare` or `wp run build` which runs `chmod-bins` |
-| `plugin.json integrity` — missing                | Claude adapter manifest absent from `@webpresso/plugin-claude` | Re-run `wp setup --host claude` or reinstall the Claude plugin    |
-| `MCP server liveness` — timeout                  | MCP server cold-start too slow                                 | Wait and retry, or run `wp hooks doctor --skip-mcp`               |
-| Any check — not found at `dist/esm/...`          | Build artifacts missing                                        | Run `wp run build` in the webpresso repo                          |
+| Check                                            | Likely Cause                                                      | Fix                                                               |
+| ------------------------------------------------ | ----------------------------------------------------------------- | ----------------------------------------------------------------- |
+| `pretool-guard` / `post-tool` / etc. — not found | `wp run build` not run after install                              | `wp run build`                                                    |
+| `pretool-guard` / etc. — not executable          | `chmod +x` not persisted                                          | Re-run `wp run prepare` or `wp run build` which runs `chmod-bins` |
+| `plugin.json integrity` — missing                | Claude or Antigravity adapter manifest absent from plugin package | Re-run `wp setup --host <host>` or reinstall the host plugin      |
+| `MCP server liveness` — timeout                  | MCP server cold-start too slow                                    | Wait and retry, or run `wp hooks doctor --skip-mcp`               |
+| Any check — not found at `dist/esm/...`          | Build artifacts missing                                           | Run `wp run build` in the webpresso repo                          |
 
 ### Updating the webpresso MCP server (monorepo authors)
 
@@ -95,10 +95,12 @@ started. Check the installed host version before using version-scoped controls.
   commands](https://dev.opencode.ai/v2/docs/cli/commands/); host documentation
   verified 2026-10-17). These `dev.opencode.ai` paths sit on a preview domain
   and can move; confirm the v2 path still resolves before following it.
+- **Antigravity:** Preferences / Settings → Plugins → reload or toggle `wp` plugin,
+  or restart the Antigravity session. Verify with `wp hooks doctor` or `wp hooks status`.
 
 After reconnecting, prove the loaded source rather than the connection:
 
-1. Call `wp_tool_surface` with `detail: "diagnostic"`.
+1. Call `tool_surface` with `detail: "diagnostic"`.
 2. Compare `details.diagnostic.live.sourceCommit` against the commit you expect
    the checkout to be serving.
 3. Read `details.diagnostic.identity.status`, which is exactly one of `current`,

package/skills/investigate/SKILL.md

@@ -19,19 +19,19 @@ flaky behavior, or confusing symptom before editing code.
 
 ## Tooling map
 
-| Need                   | Prefer                                                           |
-| ---------------------- | ---------------------------------------------------------------- |
-| Reproduce / large logs | `wp_session_execute`, `wp_session_batch_execute`                 |
-| Large files            | `wp_session_execute_file`                                        |
-| Prior continuity       | `wp_session_search`, `wp_session_restore`, `wp_session_retrieve` |
-| Capture findings       | `wp_session_capture` (short pointer, not full paste-back)        |
-| Proof runs             | `wp_test`, `wp_qa`, `wp_lint`, `wp_typecheck`                    |
-| Code search/read       | host Grep/Read first; avoid shell-as-IDE                         |
+| Need                   | Prefer                                                  |
+| ---------------------- | ------------------------------------------------------- |
+| Reproduce / large logs | `session_execute`, `session_batch_execute`              |
+| Large files            | `session_execute_file`                                  |
+| Prior continuity       | `session_search`, `session_restore`, `session_retrieve` |
+| Capture findings       | `session_capture` (short pointer, not full paste-back)  |
+| Proof runs             | `test`, `qa`, `lint`, `typecheck`                       |
+| Code search/read       | host Grep/Read first; avoid shell-as-IDE                |
 
 ## Workflow
 
 1. Reproduce or capture the failure.
-   - Run the exact failing command or trace the exact user path (prefer `wp_session_execute`).
+   - Run the exact failing command or trace the exact user path (prefer `session_execute`).
    - Keep the evidence that matters: error text, failing assertion, exit code,
      log path, or boundary mismatch.
 2. Read the whole boundary.
@@ -42,9 +42,20 @@ flaky behavior, or confusing symptom before editing code.
    - Name the broken invariant in one sentence.
    - Name the owner that should enforce it.
    - Separate facts from guesses.
+   - **Every cause must carry the observation that proved it**: the command you
+     ran, its output, and the code path that produced it. A cause you have not
+     executed against the failing case is a guess and must be labelled as one.
 4. Disconfirm cheap alternatives.
    - Test the obvious competing explanations before settling on one cause.
    - Add temporary diagnostics only when needed, and remove them after one pass.
+   - **When a cause is disproved, return to the reproduction rather than
+     replacing it with the next plausible story.** Two or three confident
+     explanations in a row, none observed, means the failure has not been
+     reproduced yet — go back to step 1.
+   - A test fixture, capability object, or recorded tool output that asserts
+     behaviour is the weakest link: confirm at least one path against the real
+     binary, module, or service it stands in for.
+   - Related: `catalog/agent/rules/evidence-discipline.md` § 6.
 5. Produce failing proof.
    - Prefer a targeted failing test.
    - If test-first is impossible at this boundary, use the nearest deterministic

package/skills/opencode-go/SKILL.md

@@ -11,8 +11,8 @@ until independently verified.
 
 ## MCP-only contract
 
-- Call `wp_review_gate` exactly once for the real plan version or delivery diff.
-- Observe the same durable operation with `wp_review_gate_wait` when needed.
+- Call `review_gate` exactly once for the real plan version or delivery diff.
+- Observe the same durable operation with `review_gate_wait` when needed.
 - Never invoke a provider command, the legacy review CLI, or a removed review-run surface.
 - If the review MCP is unavailable, stop and report it unavailable. There is no CLI fallback.
 
@@ -25,8 +25,7 @@ until independently verified.
   "purpose": "delivery",
   "base_ref": "<full-base-sha>",
   "authority_ref": "<full-head-sha>",
-  "provider": "opencode",
-  "model": "opencode-go/deepseek-v4.1-flash",
+  "caller_model": "<your own model id, exactly as your host reports it>",
   "repository_access": "none",
 }
 ```
@@ -37,13 +36,15 @@ verdict with no new review and no new round. A partial approval, withheld becaus
 is incomplete (not every prior finding was briefed, or a briefed prior claim was marked
 still-open without a matching finding), grants no authority and spends no round.
 
-## Model policy
+## Reviewer selection
 
-Default exact model: `opencode-go/deepseek-v4.1-flash`.
-Committed exact options: `opencode-go/deepseek-v4.1-flash`, `opencode-go/glm-5.3-flash`, `opencode-go/deepseek-v4-pro`, `opencode-go/kimi-k2.7-code`, `opencode-go/muse-spark-1.3-contributor`, `opencode-go/mimo-v2.6-pro`, `opencode-go/step-5-preview`, `opencode-go/qwen3.8-max`, `opencode-go/mimo-v2.6-flash`, `opencode-go/qwen3.8-flash`, `opencode-go/minimax-m3.1-flash-free`, `opencode-go/qwen3.7-plus`, `opencode-go/muse-spark-1.2-contributor`, `opencode-go/mimo-v2.5`, `opencode-go/minimax-m3`, `opencode-go/mimo-v2.5-pro`, `opencode-go/longcat-2.5-preview-free`, `opencode-go/longcat-2.0`, `opencode-go/gpt-6-luna`, `opencode-go/kimi-k3`, `opencode-go/hy4-preview`, `opencode-go/hy3`, `opencode-go/grok-4.7`, `opencode-go/gpt-5.6-luna`, `opencode-go/claude-haiku-5-5`, `opencode-go/glm-5.3`, `opencode-go/glm-5.2`, `opencode-go/gemini-4-argon-contributor`, `opencode-go/beam-free`.
-Use a named exact option when requested; otherwise use the default. Provider catalog discovery
-belongs to the snapshot drift workflow, never to a skill invocation; reading the box-local
-credential store at gate time is a local file read, not catalog discovery.
+Pass `caller_model` with your OWN model id, exactly as your host reports it, and omit
+`provider`, `model`, and `effort`: the gate selects the reviewer route itself — a cross-family
+reviewer chosen for capability, current provider limits, and measured daily cost — and reports
+the choice in `policy_selection`. Never name a reviewer model, probe a provider CLI for its
+catalog, or read a credential store to discover models at invocation time; provider catalog
+discovery belongs to the snapshot drift workflow. An operator may still pass an explicit
+`provider`/`model` as a human override; agents must not.
 
 ## Review quality
 

package/skills/plan-refine/SKILL.md

@@ -75,9 +75,10 @@ Run **1–3 (and relevant review lenses) in parallel** whenever tools allow. Do
    - Score alternatives on elegance, durability, and efficiency; keep only the winner and write the rejection rationale for heavier options.
 
 4. **Plan-review lenses (skip when the caller already ran them).** Folded `/autoplan`: run relevant CEO/founder, design, engineering, and DevEx lenses **in parallel when independent**; consolidate keep/change/drop, unresolved taste calls, tests, go/no-go.
+   - **Review cost — know it before you dispatch.** An `approve`, `approve-with-nits`, or `reject` verdict from a `review_gate` run spends ONE formal review round (per slug and purpose). A no-verdict attempt spends none; editing the plan spends and resets nothing already spent. `src/review/budgets.ts` owns the numeric allowance — never restate it in prose — and `wp review budget <slug>` reports remaining capacity live.
    - **Skip condition.** If the caller states `plan-* reviews complete for this pass`, do **not** re-run the lenses. `ralplan` runs them before handing off, so re-running them here is duplicated spend, not a second opinion.
    - **Re-entry.** If refinement itself **materially changes scope**, re-run only the affected lens — never the full set — then continue applying.
-   - **Re-review rounds.** `catalog/agent/rules/review-methodology-sota.md` Principle 5 sets the delta-anchored adjudication contract subsequent `wp_review_gate` rounds follow.
+   - **Re-review rounds.** `catalog/agent/rules/review-methodology-sota.md` Principle 5 sets the delta-anchored adjudication contract subsequent `review_gate` rounds follow.
 
 5. **Blueprint enforcement (max parallel).**
    - Split for independent execution; declare `Depends`; file-conflict CP = 0 per wave; TDD/proof steps; preserve acceptance criteria.

package/skills/ralplan/SKILL.md

@@ -42,6 +42,10 @@ Use when the user invokes `$ralplan`, asks for RALPLAN, or wants consensus plann
 1. **Blueprint is the plan.** Freeform notes are not durable consensus. Create or bind a blueprint before reviews.
 2. **Align with other lanes before planning.** This repo is worked by many concurrent agent sessions. Before the code dive, establish which surfaces another live lane already owns and record them as explicit non-goals. See [Lane alignment](#lane-alignment-not-optional). The user should not have to re-assert this.
 3. **Ground before drafting.** Code dive (+ bounded external research when needed) happens **before** the blueprint draft is treated as serious.
+   - **A stated cause is a claim that must be observed.** When a plan explains
+     why something fails, it carries the command that produced that answer.
+     An unobserved cause is a guess laundered into consensus, and review will
+     spend rounds disproving it instead of improving the plan.
 4. **Reviews before refine.** Run risk-matched `plan-*` skills on the blueprint, apply findings, **then** `/plan-refine`.
 5. **No implementation.** Do not edit product source, commit implementation, or start `ultragoal`/`team`/`autopilot` unless the user explicitly switches out of planning.
 6. **No review stampede.** Do not fan out multi-host outside-voice swarms. Prefer in-host skill loads; at most one outside voice only if the user asks or the change is auth / data-loss / public-API sensitive.
@@ -126,7 +130,7 @@ Rules:
 - Apply findings **into the blueprint** after each review (or once after the set if independent).
 - Independent reviews may run in parallel **only when** they do not depend on each other's edits; if eng findings reshape scope, re-run only the affected optional reviews.
 - Optional high-risk challenge: one sequential outside-voice pass (`codex` / `claude` / `opencode-go`) **after** eng review if the user asks or the change is auth / data-loss / public-API sensitive. Never parallel multi-host review.
-- Any formal `wp_review_gate` re-review round follows `catalog/agent/rules/review-methodology-sota.md` Principle 5's delta-anchored adjudication contract, not a fresh rediscovery pass.
+- Any formal `review_gate` re-review round follows `catalog/agent/rules/review-methodology-sota.md` Principle 5's delta-anchored adjudication contract, not a fresh rediscovery pass.
 
 ### 5. `/plan-refine` last (always)
 

package/skills/team/SKILL.md

@@ -9,7 +9,7 @@ related: [autopilot, goal, plan-refine, verify, handoff]
 created: "2026-07-13"
 last_reviewed: "2026-07-21"
 name: team
-description: "Coordinate multiple dashboard-backed agent sessions on one task."
+description: "Coordinate multiple agent work lanes with a leader-owned task list."
 argument-hint: "<brief|role plan>"
 ---
 
@@ -18,38 +18,39 @@ argument-hint: "<brief|role plan>"
 Use `team` when the work needs coordinated parallel lanes with a leader-owned
 task list, explicit handoffs, and independent verification. Prefer native
 subagents for small bounded lookups; use `team` when the parallel work should be
-visible, durable, and operator-controllable from `wp dash`. Prefer `ultragoal` +
-`/goal` (autopilot) when the work is blueprint-owned and does not need
-multi-provider dashboard lanes.
+visible and durable across a larger effort. Use Webpresso Desktop to manage
+interactive provider sessions. Prefer `ultragoal` + `/goal` (autopilot) when the
+work is blueprint-owned and does not need separately managed work lanes.
 
 ## Tooling map
 
-| Need                  | Prefer                                                          |
-| --------------------- | --------------------------------------------------------------- |
-| Dashboard / sessions  | `wp dash`, `wp_fleet_status`, `wp_worker_tail`                  |
-| Worktrees             | `wp_worktree` per lane                                          |
-| Context-light handoff | `wp_session_context` (required before spawn — no history paste) |
-| Continuity            | `wp_session_capture` / `search` / `restore`                     |
-| Blueprint tasks       | `wp_blueprint_task_verify` only for completion                  |
-| QA                    | `wp_qa` / targeted `wp_test` / `wp_lint` / `wp_typecheck`       |
-| PR                    | `wp_pr_upsert` / `wp_pr_status` / `wp_pr_wait`                  |
+| Need                  | Prefer                                                       |
+| --------------------- | ------------------------------------------------------------ |
+| Interactive sessions  | Webpresso Desktop                                            |
+| Worktree visibility   | `wp fleet status`, `fleet_status`                            |
+| Worktrees             | `worktree` per lane                                          |
+| Context-light handoff | `session_context` (required before spawn — no history paste) |
+| Continuity            | `session_capture` / `search` / `restore`                     |
+| Blueprint tasks       | `blueprint_task_verify` only for completion                  |
+| QA                    | `qa` / targeted `test` / `lint` / `typecheck`                |
+| PR                    | `pr_upsert` / `pr_status` / `pr_wait`                        |
 
 ## Protocol
 
 1. Start from a grounded brief or an approved blueprint. If scope is vague, run
    `plan-refine` first and define task lanes, shared files, budgets, and verification.
-2. Open or reuse `wp dash` and launch the provider sessions needed for the
-   lanes. Direct `wp claude`, `wp codex`, and `wp opencode` commands are
-   expected to enter the dashboard in interactive terminals.
+2. Open Webpresso Desktop and launch the provider sessions needed for the
+   lanes. The `wp claude`, `wp codex`, and `wp opencode` commands
+   remain available for direct CLI launches.
 3. Assign one owner per lane. Include the task, allowed files or surfaces,
    expected output, verification command, and blocker-report rule.
-4. Before each worker spawn, build a bounded manifest with `wp_session_context`
+4. Before each worker spawn, build a bounded manifest with `session_context`
    (objective, constraints, evidence refs, remaining steps). Never copy parent transcripts.
 5. Keep one lane or leader pass responsible for integration and evidence.
    Workers report findings, patches, tests, and unresolved risks; they do not
    self-approve or mark blueprint tasks complete.
 6. Integrate only after checking shared-file conflicts, updated assumptions,
-   and verification evidence. Use `wp_blueprint_task_verify` for task completion
+   and verification evidence. Use `blueprint_task_verify` for task completion
    when a blueprint owns the work.
 7. Stop when every lane is complete, cancelled, or explicitly blocked and the
    leader has recorded verification evidence (≤40-line handoff if blocked).
@@ -66,6 +67,49 @@ multi-provider dashboard lanes.
 - Never bypass review provenance, push to main, self-approve, or increase
   timeouts to hide coordination failures.
 
+### Capped host messaging
+
+- Pull-first routing: routine assignment, status, and attention flow goes
+  through the durable source and the existing pull surfaces (`fleet_status`
+  role / `wp fleet status` / `worker_tail` / `session_context`);
+  cross-session sends are reserved for a blocker, a decision, a changed
+  priority, or one availability canary. Judgment sends (a decision, a
+  changed priority, a blocker escalation that changes another lane's
+  authority) ride the typed request envelope (ADR 0004; the
+  `quota-and-purpose-routing-policy` blueprint owns that surface) — until
+  it ships, name the request in the outbox or manifest entry instead of
+  free-form text.
+- Bounded, degradable pulls: slow or degraded pull surfaces return partial
+  results plus warnings — never hang, and never raise timeouts to hide it
+  (`no-timeout-as-fix`); a degraded read is a decision input, not something
+  to spend a send on.
+- Counted discipline: every send attempt counts, refused and queued included.
+  Warn at six, stop routine sends at eight, and reserve two control slots; the
+  canary draws from the reserve, and the reserve is strictly rationed — one
+  send per genuinely new control event. The numbers assume the observed ~10
+  sends per user turn as of 2026-10-31 (the anthropics/claude-code#94000
+  thread reports variance across builds); rescale proportionally if the
+  observed cap differs. The running count and last canary result live in the
+  outbox header and the `session_capture` record; on resume or after
+  compaction, re-read them before any send.
+- Send overflow queues to the outbox — a durable coordinator-owned queue
+  file. Where no fleet outbox exists, create one: a single
+  coordinator-owned markdown file at a stable path (the fleet protocol's
+  outbox path where the protocol defines one, otherwise one
+  coordinator-named path recorded in the two anchor homes) whose header
+  carries owner, path, attempt count, last canary result, and timestamp;
+  name it in the `session_capture` record and the next handoff
+  manifest. The manifest is the queue of record until the outbox exists.
+- A pause closes the channel: queue in the leader's durable outbox and never
+  route around it — no relays, peers, new sessions, schedulers, filesystem
+  push-delivery to peers, configuration changes, or
+  alternate transports/tools, including any uncapped or legacy send interface. The
+  outbox is pull-read durable state, so pull-reading it is not a route-around;
+  the next genuine user turn is the reopening test.
+- Supersession check: before acting on a queued order, check durable state for
+  a newer arbitration — queued sends deliver late and out of order (observed
+  2026-10-24).
+
 ## Output
 
 Report:

package/skills/tech-debt/SKILL.md

@@ -25,7 +25,7 @@ Manage the tech-debt lifecycle using `wp tech-debt` commands.
 
 `new` (dry runs included) refuses a root that `wp audit committed-state-paths`
 forbids adding to, such as this repository's `tech-debt/`. There, record a new
-follow-up as a blueprint task (MCP `wp_blueprint_put`) or a draft blueprint
+follow-up as a blueprint task (MCP `blueprint_put`) or a draft blueprint
 (`wp blueprint new`) instead. The examples below apply only where that audit
 permits the resolved root.
 

package/skills/tooling-friction/SKILL.md

@@ -47,10 +47,30 @@ Optional post-land **product signal** for MCP/CLI/hooks/CI pain so Webpresso too
 4. Write the capture with the validating verb — it is the only writer, and it
    puts the document at the central, repo-scoped desktop state surface:
 
+   First write the capture JSON to a scratch file with the host's file-write
+   tool, under the scratch directory `$TMPDIR/webpresso/scratch/` (outside every
+   worktree, per the agent scratch write policy; never the repo root, and never
+   committed). Resolve that directory to an **absolute path** yourself and use
+   the literal path below — hosts refuse a command that carries a shell
+   variable expansion. Then hand the file to the verb with `--from-file`; no
+   pipe, redirect or shell variable is involved:
+
+   ```bash
+   wp tooling-friction write --file YYYY-MM-DD-<slug|pr|session>.json --from-file <absolute-scratch-dir>/tooling-friction-capture.json
+   ```
+
+   If your `wp` predates `--from-file`, **redirect** the same file to stdin
+   instead:
+
    ```bash
-   printf '%s' "$CAPTURE_JSON" | wp tooling-friction write --file YYYY-MM-DD-<slug|pr|session>.json
+   wp tooling-friction write --file YYYY-MM-DD-<slug|pr|session>.json < <absolute-scratch-dir>/tooling-friction-capture.json
    ```
 
+   Do not pipe a shell variable into the verb (`printf '%s' "$CAPTURE_JSON" | …`):
+   hosts refuse the unresolvable expansion, and the fallback — writing the JSON
+   straight into the store — skips validation, which is how a capture with ten
+   schema issues reached disk. Never write the capture into the store yourself.
+
    The verb parses the document through the shared schema helper **before** it
    touches disk, so a capture that violates v1 is refused (non-zero exit,
    naming every failing field path) and nothing is written. It prints the
@@ -63,7 +83,7 @@ Optional post-land **product signal** for MCP/CLI/hooks/CI pain so Webpresso too
    verb's printed path matches:
 
    ```text
-   wp_tooling_friction_path({"file":"YYYY-MM-DD-<slug|pr|session>.json"})
+   tooling_friction_path({"file":"YYYY-MM-DD-<slug|pr|session>.json"})
    → summary: tooling-friction path: <absolute-path>
    ```
 
@@ -84,17 +104,17 @@ Optional post-land **product signal** for MCP/CLI/hooks/CI pain so Webpresso too
    worktree or `.agent/` path.
 
 5. Optional `--promote` or severity `high`/`critical`: record the follow-up as
-   a blueprint task (MCP `wp_blueprint_put`) or a draft blueprint
+   a blueprint task (MCP `blueprint_put`) or a draft blueprint
    (`wp blueprint new`), and set `promoted_to` to that blueprint path. Do not
    use `wp tech-debt new` here: it refuses this repository's `tech-debt/` root,
    which `wp audit committed-state-paths` forbids adding to.
-6. Optional one-line `wp_session_capture` pointer to the JSON path — no paste-back walls.
+6. Optional one-line `session_capture` pointer to the JSON path — no paste-back walls.
 
 **Rate limit:** at most **one** capture per verify bookend.
 
 ## Store path (SSOT)
 
-`wp_tooling_friction_path({"file":"<file>"})` (or the human CLI projection
+`tooling_friction_path({"file":"<file>"})` (or the human CLI projection
 `wp tooling-friction path --file <file>`) — a read-only projection of the pure
 preferred state root (WP_STATE_ROOT or env-paths data; no writability fallback)
 plus `repoIdentityV1(git-common-dir)` under `tooling-friction/<file>`. This
@@ -126,10 +146,10 @@ also include `path`, `repoKey` (16-hex), `stateRoot`, `scope: "repo"`, and
       "id": "tf-status-ci-skew",
       "severity": "high",
       "surface": "pr",
-      "tool": "wp_pr_status",
+      "tool": "pr_status",
       "kind": "friction",
       "signal": "status_ci_skew",
-      "symptom": "wp_pr_merge blocked while GitHub CLEAN and PR Policy green.",
+      "symptom": "pr_merge blocked while GitHub CLEAN and PR Policy green.",
       "token_waste": "high",
       "time_waste_minutes": 25,
       "recurrence": "session",
@@ -168,9 +188,9 @@ also include `path`, `repoKey` (16-hex), `stateRoot`, `scope: "repo"`, and
 
 **Good**
 
-- `wp_pr_merge: land readiness disagrees with GitHub CLEAN / PR Policy (status_ci_skew, high)`
-- `wp_review_gate: re-approve after ledger-only commits; subject binding unclear (retry_loop, medium)`
-- `wp_pr_upsert: bare Review model "Kimi" fails provider regex; needs "kimi reviewer" (schema_confuse, low)`
+- `pr_merge: land readiness disagrees with GitHub CLEAN / PR Policy (status_ci_skew, high)`
+- `review_gate: re-approve after ledger-only commits; subject binding unclear (retry_loop, medium)`
+- `pr_upsert: bare Review model "Kimi" fails provider regex; needs "kimi reviewer" (schema_confuse, low)`
 
 **Bad**
 
@@ -191,7 +211,7 @@ also include `path`, `repoKey` (16-hex), `stateRoot`, `scope: "repo"`, and
 9. **Never invent the capture path** — no fleet folder slugs
    (`github.com-org-repo-*`), no worktree-keyed desktop-state, no guessing
    under `Application Support` or `~/.webpresso`. Always call
-   `wp_tooling_friction_path` / `wp tooling-friction path` and write to the
+   `tooling_friction_path` / `wp tooling-friction path` and write to the
    absolute path it returns
 
 ## Integration
@@ -203,7 +223,7 @@ also include `path`, `repoKey` (16-hex), `stateRoot`, `scope: "repo"`, and
 ## Output (agent reply)
 
 ```text
-tooling-friction: wrote desktop state <absolute-path-from-wp_tooling_friction_path>
+tooling-friction: wrote desktop state <absolute-path-from-tooling_friction_path>
 findings: 2 (high=1, medium=1)
 promoted: none | blueprints/<lifecycle>/<slug> | tech-debt/...
 ```