@1aboveio/skills 1.0.16 → 1.0.17

package/skills/core/editorial-review/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: editorial-review
 description: "Review a document or generated report for what it says (does the reader get the answer, is the argument sound, is anything unsupported, obvious or repeated), then fix the content. Use to review, tighten or clarify a doc or report, and as the review step of write-doc, write-report and domain report skills. NOT for Chinese wording (polish-cn) or code review (better-review)."
-release-version: 0.48.0
+release-version: 0.48.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Editorial review

package/skills/core/house-style/SKILL.md

@@ -3,7 +3,7 @@ name: house-style
 description: "Shared reference the writing skills read by path: WRITING.md lookup and precedence, template choice, gap markers, template shape, the bundled templates, and the default English and Chinese style guides. Never select or invoke it as a task."
 disable-model-invocation: true
 user-invocable: false
-release-version: 0.48.0
+release-version: 0.48.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # House style

package/skills/core/plain-language/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: plain-language
 description: "Session mode: every reply and status line in plain language — lead with the point, everyday words, full sentences, no filler — in English or Chinese, until turned off. Enable by default when the project has an applicable WRITING.md, even without a slash command. Use for /plain-language, 'talk plainly', '说人话', and explicit requests to remember project reply preferences; /plain-language init persists the default and loading instructions. Save reply rules only under Agent replies; route document preferences to distill-writing. Ordinary mode toggles remain session-only. Turn off with '/plain-language off' or 'normal mode'. NOT for writing a document (write-doc) or analytical report (write-report) or reviewing one (editorial-review)."
-release-version: 0.48.0
+release-version: 0.48.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Plain language

package/skills/core/polish-cn/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: polish-cn
 description: "Polish the Chinese wording of a finished document or report, with a script proving every number, date, identifier, link and protected term is unchanged; prefers a Chinese model and records which ran. Use for '中文润色' or as a report skill's last step. NOT for cutting or restructuring content (editorial-review) or translating (write-doc or write-report)."
-release-version: 0.48.0
+release-version: 0.48.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Polish Chinese

package/skills/core/reg-parser/SKILL.md

@@ -2,7 +2,7 @@
 name: reg-parser
 version: 1.1.0
 description: "Parse regulatory/scheme documents into structured outputs: convert a regulation (AML, VARS, PCI-DSS, KYC, GDPR) into an audit-ready compliance checklist, or trace contract clauses to a mandate source. Suggest proactively when a regulation PDF accompanies a contract review or compliance task. NOT general summarization (doc-to-md), writing a gap-analysis report (write-report), or writing a policy from the checklist (write-doc)."
-release-version: 0.48.0
+release-version: 0.48.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # reg-parser

package/skills/core/terminology/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: terminology
 description: "Build and keep a project's TERMINOLOGY.md: the preferred term per concept in English, 简体 and 繁體, and the terms to avoid. Use to set it up from the project's documents, when the user settles or corrects a term, or when another writing skill needs the format. NOT for writing documents (write-doc) or analytical reports (write-report) or the code domain model (domain-modeling)."
-release-version: 0.48.0
+release-version: 0.48.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Terminology

package/skills/core/write-doc/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: write-doc
 description: "Write or edit documents that define or propose something: BRD, PRD, technical spec, integration guide, proposal, policy or risk procedure; English, Chinese or bilingual. Use automatically for drafting or revising these documents. Markdown by default; export when requested. NOT for analytical reports or writing up findings (write-report), ordinary chat replies (plain-language), learning style or saving preferences alone (distill-writing), performing an audit (compliance-audit), or WeChat articles (wechat-article-writer)."
-release-version: 0.48.0
+release-version: 0.48.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Write a document

package/skills/core/write-report/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: write-report
 description: "Write or edit analytical reports from data, research, analysis or findings: payment, fraud, operational, performance, research, gap-analysis, audit, external assessment, management and Visa VARS reports. Use whenever asked to report results, write up findings, or turn analysis into a report, even without naming this skill. English, Chinese or bilingual; Markdown by default, export when requested. NOT for defining requirements, policies or proposals (write-doc), performing the underlying domain analysis or audit, chat-only answers (plain-language), or learning house style (distill-writing)."
-release-version: 0.48.0
+release-version: 0.48.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Write an analytical report

package/skills/engineering/better-review/SKILL.md

@@ -4,7 +4,7 @@ description: "Slash/explicit-only (/better-review). Single-agent adversarial rev
 disable-model-invocation: true
 dependencies:
   - engineering-runtime
-release-version: 0.48.0
+release-version: 0.48.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Better Review

package/skills/engineering/e2e-test/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: e2e-test
 description: "Playwright end-to-end guidance for affected browser journeys, render health and presentation checks, with route manifests and sweeps for broader audits. Use when browser routes or user flows ship or change, or a Playwright test flakes. NOT for non-browser tests, defining what to test (ensure-coverage), the curated ALIVE/DEAD golden-path gate (golden-path), or CI workflow YAML (github-actions)."
-release-version: 0.48.0
+release-version: 0.48.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # E2E Testing Standard

package/skills/engineering/engineering/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: engineering
 description: "Engineering conventions: feature-delivery priorities, focused verification and review, operational boundaries, and tracker routing. Standalone /engineering offers Global, Project, or Session setup and targeted resets for configured scopes; /engineering init keeps explicit project setup. Use when setting up AGENTS.md or CONTRIBUTING.md, saving or resetting engineering defaults, or before creating an engineering issue, spec, epic, ticket, or sub-issue on GitHub or Linear. Reads existing policy without writing during ordinary work. NOT the issue-to-PR workflow (resolve-issues), release execution (resolve-release), Git delivery (github-flow), or CI setup (github-actions)."
-release-version: 0.48.0
+release-version: 0.48.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Engineering

package/skills/engineering/engineering-runtime/SKILL.md

@@ -3,7 +3,7 @@ name: engineering-runtime
 description: Internal support package for shared Engineering Workflow executable behavior. Never select or invoke this package as a user capability.
 disable-model-invocation: true
 user-invocable: false
-release-version: 0.48.0
+release-version: 0.48.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Engineering Runtime

package/skills/engineering/engineering-runtime/coherence/workflow.json

@@ -369,7 +369,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "3204ec23d0c79b0a5df8af2cf3a68a3bf839087b29969c74f5258ca8d156571b",
+      "contentDigest": "0ee641d7c1c90df5d1ca4d4f516f3aec0236ae224f2cfdf5e69a8d0023d0224f",
       "digestExcludes": []
     },
     {
@@ -382,7 +382,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "6e0d37af1ed2c9e38958d8ebb4f3c021491c2a8dd2fd12304d4b28159949b3c0",
+      "contentDigest": "b0c6b061b9d99a3fdf61ee41a3380986f8b0e6f687fc14158071ba5cfc4ad231",
       "digestExcludes": []
     },
     {
@@ -395,7 +395,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "a551b109b523dfd00d67402b38f130014207be98d2ccf524a768add85ab85911",
+      "contentDigest": "00afe10ecfc7fb382a3c9ddf7cfb1264eeeb003e935c3fd8eee09af7f0e6dc4c",
       "digestExcludes": []
     },
     {
@@ -408,7 +408,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "0d0a49fd2245eea13d6b994457e64450f7cec96b920c525138905fcfba5e2f44",
+      "contentDigest": "807efefc218519809541349ebc10358d37c5688d5d657fe2a58dc85e2a9aa055",
       "digestExcludes": []
     },
     {
@@ -421,7 +421,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "572b27835ce6883e3fbd8f7db6ba29a1c3a2e3a1217367bc08bf8cdce1f0ae9a",
+      "contentDigest": "efb97f0e66dec6c2d6894a1feb128892f6974d9aa71c83a29acabf22852f2228",
       "digestExcludes": []
     },
     {
@@ -434,7 +434,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "303f82fb4fd519446ecbb5b599ab179bec7ec74b2d160c0456ff841b97ff807d",
+      "contentDigest": "a54c0d8d50bd9de11b98118072a87f1fefb1930e4936eae4ad1c8d369125e80b",
       "digestExcludes": []
     },
     {
@@ -447,7 +447,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "b0823ca9b218d171039a5d86b3038afe6cbc9a0be96848e060ef6c198882ae5a",
+      "contentDigest": "2700f926acbfc82dec992a81f42373f5ac03d8e6cdfd9288e447e72e4215ca11",
       "digestExcludes": []
     },
     {
@@ -460,7 +460,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "90ae8a3116dff8510a5511ef58a15d6bd632eaa61ad192911399c8d2bd0c56a3",
+      "contentDigest": "a00c2848f686ee2d4775661f87c2569b4810480233f4a0649ca995f0bebdb2a8",
       "digestExcludes": []
     },
     {
@@ -473,7 +473,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "13df8c9fbfaeca374d1eccf278026515d3cefe05092693ad3789351982271c38",
+      "contentDigest": "27b87c7ac54bfc217ffe5c68fae0a9d9b1dd8619286c470ca721200bb6962bd8",
       "digestExcludes": []
     },
     {
@@ -486,7 +486,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "36fcee2a585b71c6b391a8d44a9378503f35715c83cd487c4b9e6fee35300ab5",
+      "contentDigest": "a67d55dda1c9278b16d192efe28d2827d2a1010b7c14bde8bf3ac10ce78adf13",
       "digestExcludes": []
     },
     {
@@ -499,7 +499,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "801d2c483d76803864eb4cb34e6e0981e1039eba4a9533e94ad6f9075416cb73",
+      "contentDigest": "15626fe123fbf537b89af3cb34349430fc1c76c4ad04e8853f6e761c7f45db30",
       "digestExcludes": []
     },
     {
@@ -512,13 +512,13 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "4cacea8ee67f05aabb5b16485e6093e6d2b5524ae25398fe28fefb8e6302bea7",
+      "contentDigest": "1bdafd5f8149b4020319869ae83c17734cec9c2c52f7dc28d5c672985ca73111",
       "digestExcludes": [
         "coherence/workflow.json"
       ]
     }
   ],
-  "releaseIdentity": "9301ab0617c9f8d93c8e58cb6b37e3e3d487efdf24036c4c99a1defc08345e08",
+  "releaseIdentity": "446559a9feac423ab3c67e5b391ea300aeb1e5a80ec94a66a69062025e47a87a",
   "lifecycleAuthority": "native-skills-cli",
   "repairRecipe": {
     "id": "engineering-workflow-dependency-first",

package/skills/engineering/ensure-coverage/SKILL.md

@@ -2,7 +2,7 @@
 name: ensure-coverage
 description: "Define or audit behavior-first test criteria — ACs, required test levels, mock/integration/E2E policy — across three axes: breadth (Coverage Ledger), depth (over-mocking), presentation (perceivability of browser surfaces). NOT judging whether a single test is any good (test-quality), authoring browser tests (e2e-test), reviewing a PR (better-review), or delivering issues (resolve-issues)."
 disable-model-invocation: true
-release-version: 0.48.0
+release-version: 0.48.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Ensure Coverage

package/skills/engineering/golden-path/SKILL.md

@@ -3,7 +3,7 @@ name: golden-path
 description: "Golden-path E2E: the short list of user journeys whose failure blocks a release, kept in a repo as one contract (golden-paths.json) with a generated GOLDEN_PATHS.md and a generated GitHub Actions workflow, and run against a local build or a deployed URL for an ALIVE/DEAD verdict. Use to set golden paths up in a repo ('init golden paths', 'add golden-path CI'), to migrate an older smoke.manifest.json or a hand-built smoke setup ('audit', 'migrate smoke'), to add, change, or remove a golden path, to ask 'is the build alive?' or run them before a PR or release, or when a change touches a flow listed in GOLDEN_PATHS.md. NOT for writing the Playwright specs themselves (e2e-test), deciding what a change must prove (ensure-coverage), or general workflow YAML (github-actions)."
 dependencies:
   - e2e-test
-release-version: 0.48.0
+release-version: 0.48.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Golden path

package/skills/engineering/harness-runtime/SKILL.md

@@ -3,7 +3,7 @@ name: harness-runtime
 description: Internal import-only library shared by first-party engineering packages. Not a workflow skill; never select or invoke it as a user capability.
 disable-model-invocation: true
 user-invocable: false
-release-version: 0.48.0
+release-version: 0.48.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Harness Runtime

package/skills/engineering/harness-runtime/agent-catalog.mjs

@@ -620,7 +620,8 @@ export function buildCatalogRequest({
   if (normalizedAvailable.available.length === 0) {
     return blocked(
       AGENT_CATALOG_BLOCK_CODES.CAPABILITIES_MISSING,
-      'no current-turn models were supplied; the harness must advertise its available models for this turn',
+      'no current-turn models were supplied: the resolver input has no available[] entries; '
+        + 'collect verified host model and effort evidence before retrying; this does not establish that the harness lacks worker support',
     )
   }
   if (foregroundModel !== null && foregroundModel !== undefined && !nonEmptyString(foregroundModel)) {

package/skills/engineering/resolve-issues/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: resolve-issues
-description: "Slash/explicit-only (/resolve-issues). Drive an issue, epic, or feature spec to reviewed, green PRs, one per issue, merged or handed back merge-ready: preflight, task map, exploration and a per-issue slice check, isolated implementers within live host capacity, then per issue its PR, independent better-review, CI, and queue/merge (or merge-ready hand-back) as soon as it is done. Asks once, at the end of preflight (target branch, merge mode, scheduler mode, plan) and resolves the worker roles' models as run metadata instead of asking, then never blocks on the human; small non-blocking problems collect in a dropbox, posted at the end as grouped ready-for-agent issues. /rush-issues is its no-questions shortcut. Do not auto-select. Use for whole-spec delivery, including high-risk work; risk changes model and validation depth, never the workflow. NOT for release work (resolve-release)."
+description: "Slash/explicit-only (/resolve-issues). Drive an issue, epic, or feature spec to reviewed, green PRs, one per issue, merged or handed back merge-ready: preflight assessment with an explorer only for planning unknowns, a per-issue slice check, isolated implementers within live host capacity, then per issue its PR, independent better-review, CI, and queue/merge (or merge-ready hand-back) as soon as it is done. Asks once, at the end of preflight (target branch, merge mode, scheduler mode, plan) and resolves the worker roles' models as run metadata instead of asking, then never blocks on the human; small non-blocking problems collect in a dropbox, posted at the end as grouped ready-for-agent issues. /rush-issues is its no-questions shortcut. Do not auto-select. Use for whole-spec delivery, including high-risk work; risk changes model and validation depth, never the workflow. NOT for release work (resolve-release)."
 disable-model-invocation: true
 metadata:
   workflow-role: coordinator
@@ -8,7 +8,7 @@ dependencies:
   - better-review
   - golden-path
   - harness-runtime
-release-version: 0.48.0
+release-version: 0.48.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Resolve issues
@@ -54,7 +54,7 @@ after 2 fix rounds without a new low of open P0/P1 path rows; no fixed round cap
 
 ```text
 preflight: ready label -> model fills -> plan draft
-  -> exploration -> size check (only scope or an open question holds a unit, with a split)
+  -> preflight assessment (optional explorer) -> size check (only scope or an open question holds a unit, with a split)
   -> one approval (target branch, merge mode, scheduler mode, plan)
   -> schedule runnable units within live host capacity:
        prepare a unit's workspace when its first worker is admitted (never all units up front)
@@ -77,9 +77,9 @@ Read each procedure right before its stage; never substitute your own.
 
 | Stage | Procedure |
 |---|---|
-| Preflight: ready label, models, plan draft, exploration, size check, approval; what any filed text may say | [references/preflight.md](references/preflight.md) ([Filed text](references/preflight.md#filed-text)) |
+| Preflight: ready label, models, plan draft, assessment, size check, approval; what any filed text may say | [references/preflight.md](references/preflight.md) ([Filed text](references/preflight.md#filed-text)) |
 | Task plan shape and live board | [references/task-plan.md](references/task-plan.md) |
-| Exploration (preflight step 4) | [references/exploration.md](references/exploration.md) |
+| Preflight assessment and optional exploration (step 4) | [references/exploration.md](references/exploration.md) |
 | Implementation loop and opening each PR | [references/implementation.md](references/implementation.md) |
 | Read-only warehouse canary | [references/canary.md](references/canary.md) |
 | Owned workspaces: plan, prepare, cleanup, recover, inventory | [references/workspaces.md](references/workspaces.md) |
@@ -105,7 +105,8 @@ Read each procedure right before its stage; never substitute your own.
   check. When a journey or case you run fails, copy its `NATIVE_FAILURE` line (or the failing step, error and
   evidence path) into the unit's plan row; an exit code alone is not a failure record.
   Leave code changes to workers so your attention stays on scheduling, and record each worker as the
-  unit's `workerKind` (`implement`, `fix`, `review`). Exploration continues the run's one explorer. After a context compaction, read this file in
+  unit's `workerKind` (`implement`, `fix`, `review`). You own preflight findings;
+  delegate unresolved planning unknowns under [exploration.md](references/exploration.md#choose-the-owner). After a context compaction, read this file in
   full again before your next step: the summary keeps the run's state, not these rules. Fill
   free slots before starting your own work, stay within [expire.md](references/expire.md)'s limit, and send
   large output to files (read only the lines you need). Expect Pi's **Completions while busy: Steer active run**
@@ -149,12 +150,13 @@ Follow [preflight.md](references/preflight.md):
 efforts are run metadata, never a question.
 2. **Provisional target:** the default branch.
 3. **Plan draft:** one unit per issue, links, delivery mode; show the board.
-4. **Exploration:** have one explorer record each unit's `slice` and,
-   separately, its `proof`, in every run; reuse prior findings for units
+4. **Preflight assessment:** record each unit's `slice` and,
+   separately, its `proof`, yourself for clear work; use an explorer only
+   for concrete planning unknowns. Reuse prior findings for units
    whose evidence did not change
    ([exploration.md](references/exploration.md#reuse-first)).
 5. **Size check:** run `size-check.mjs` (exit 0; read `verdict`). On `hold` or `stop`, hold the listed
-   units (their dependents wait, not started) and draft their splits (yours when none is drafted); on `exploration-unfinished`, continue the explorer.
+   units (their dependents wait, not started) and draft their splits (yours when none is drafted); on `exploration-unfinished`, complete the findings using step 4's owner routing.
 6. **Approval:** ask once for target, merge mode, scheduler mode, and plan;
    record the answers; plan each unit's branch, workspace, base, and lifecycle
    intent, and prepare a workspace only when its first worker is admitted

package/skills/engineering/resolve-issues/references/exploration.md

@@ -1,16 +1,44 @@
 # Exploration
 
-**One explorer per run, after the plan draft, records what sizes, orders, and
-blocks the units: behaviors, missing prerequisites, proof, line estimates,
-dependencies, contracts, and the questions that hold a unit.**
+**Every run gets a coordinator-owned preflight assessment after the plan draft:**
+behaviors, missing prerequisites, proof, line estimates, dependencies, contracts,
+and the questions that hold a unit. A dedicated explorer is optional.
 In a one-unit run, leave `contracts`, `dependsOn`, and `stacksOn` empty.
 
-## Spawn
+## Choose the owner
+
+Read the issues, applicable repository guidance, and the few code or test paths
+needed to check the plan. For clear, bounded work, write the findings yourself.
+The findings are planning state, not product code; keep detailed code discovery
+with implementers.
+
+Delegate when a concrete unknown could change the plan: uncertain cross-unit
+dependencies or contracts, unclear boundaries or likely splitting, or an unfamiliar
+validation setup. Name the unknown and the affected units in the explorer's brief.
+Multiple units or a high-risk label alone do not require an explorer; unresolved
+planning uncertainty does. An unanswered product decision stays an open question,
+not an invitation for the explorer to invent a requirement.
+
+Use the same record and size check for both paths. Resolve each unit's planning
+unknowns or record its open human decision before approval. On later scope or base
+changes, apply this routing again only to affected units.
+
+Resolve the assessment target to an exact commit before reading code: initially
+the provisional target, then the approved target after a branch change. Record
+that SHA as findings `base`; use it explicitly for reuse checks and any explorer
+checkout. The coordinator's current branch is not evidence of the assessment target.
+
+## Optional explorer
+
+Use at most one explorer at a time per run, on the fleet `explore` row, within
+live host capacity. Reuse that explorer for further investigation when available.
+Give it only the affected units and unknowns. While it writes findings, it owns
+that file exclusively; collect its result before the coordinator updates it.
 
 | Field | Value |
 |---|---|
 | Model | The explorer fill ([preflight.md](preflight.md#1-model-slots)) |
-| Workspace | Read-only checkout of the provisional target; write only the findings directory |
+| Workspace | Read-only checkout at the assessment target SHA; write only the findings directory |
 | Task plan | Absolute `task-plan.json` path; its unit ids key the findings |
 | Prior findings | Newest `.resolve-issues/rush/*/exploration/findings.json` for the same spec locator, if any |
 | Deadline | 15 minutes, plus 1 minute per unit beyond 4 |
@@ -18,15 +46,23 @@ In a one-unit run, leave `contracts`, `dependsOn`, and `stacksOn` empty.
 
 ## Reuse first
 
-**When prior findings exist, explore only the units whose evidence changed.**
-Run, before spawning, and give the explorer its output:
+**Reuse requires unchanged requirements as well as unchanged code evidence.**
+First compare each unit's current criteria, dependency contracts, relevant guidance,
+and recorded decisions with the prior assessment. Reassess affected units even if
+the helper below says `reuse`; it checks Git evidence paths, not those inputs.
+When the prior inputs cannot be established, reassess that unit.
+
+Run the code-evidence check against the exact assessment target, not the caller's
+`HEAD`; include the output and any forced reassessments in an explorer brief:
 
 ```bash
 node <skill-base-dir>/scripts/findings-reuse.mjs \
-  --prior <prior findings.json> --units <this run's unit ids, comma-separated>
+  --prior <prior findings.json> --units <this run's unit ids, comma-separated> \
+  --head <assessment-target-SHA>
 ```
 
-- `reuse`: copy the entry unchanged, with the new `base`.
+- `reuse`: copy the entry unchanged only when the non-code inputs above also
+  match, with the new `base`.
 - `recheck`: re-explore the entry; its `changed` files are where to look.
 - `new`: explore from scratch.
 
@@ -34,7 +70,9 @@ Example: a resumed run starts after earlier units merged `src/charge/`; only
 the two units whose evidence names `src/charge/` are re-explored, the other
 four are copied.
 
-## Brief
+## Assessment record
+
+The coordinator and any delegated explorer use these rules:
 
 1. **Scaffold, then save one unit at a time.** Keep an existing
    `findings.json`; otherwise create it with `version: 2`, the `base` SHA,
@@ -106,7 +144,7 @@ four are copied.
        journey; `local` runs that Charge journey script on an owned emulator,
        not the repository's default phone journey.
      - Findings saved before `local` and `skill` existed are unfinished:
-       continue the explorer to add them, even when reusing the rest.
+       add them before the size check, even when reusing the rest.
    - `physical`: evidence only a real device gives; else empty.
 
    - `groups` and `setups` (only when `slice.newProductBehaviorCount` is
@@ -193,10 +231,14 @@ it then.
 
 ## Completion
 
-Confirm the findings exist, the model read-back matches, and no product source
-changed. Never edit the findings yourself. Run the size check; on `exploration-unfinished` or
-tool failures, continue the explorer with the errors. At the deadline, have it
-save what it has and stop; continue it in the same directory for the units
-still empty while size-check problems plus empty units reach new lows, then follow
-[expire.md](expire.md). Never skip exploration;
-reuse is not skipping.
+Confirm the findings exist and no product source changed. For delegated work,
+also confirm the model read-back matches and inspect the result. Run the size
+check; `exploration-unfinished` means complete or repair the findings, not spawn
+a worker automatically. Correct a missing field yourself when the evidence is
+clear; continue the explorer only for unresolved investigation.
+
+At an explorer's deadline, have it save what it has and stop. Inspect its partial
+findings, complete clear entries yourself, and continue investigation only for
+remaining unknowns while size-check problems plus empty units reach new lows;
+then follow [expire.md](expire.md). Finish the fleet `explore` row once the
+assessment and size check are complete, even when no explorer was needed.

package/skills/engineering/resolve-issues/references/implementation.md

@@ -76,7 +76,7 @@ the same work. A passing setup check is not a substitute for the blocked behavio
 No additional report or result schema is required.
 
 Have the implementer treat findings as leads, find its own code, and report
-any `product`, `scope`, `design`, or `approval` question the explorer missed and any
+any `product`, `scope`, `design`, or `approval` question the assessment missed and any
 human-only proof. Report each question in the result's `decisionNeeded`
 ([expire.md](expire.md#decide-before-you-defer)); add each proof as a
 handback step. Never edit `findings.json`.

package/skills/engineering/resolve-issues/references/preflight.md

@@ -11,10 +11,22 @@ until step 6.
 node <skill-base-dir>/scripts/plan-sync.mjs --find-run --runs .resolve-issues/rush --issue <owner/name#123>
 ```
 
-When it prints a directory, resume that run (`next-actions.mjs --run <dir> --resume` with
-[fresh capacity](implementation.md#live-capacity))
-instead of starting another; its plan picks up whatever the tree gained
-since. It exits 0 whether or not it found a run: no run prints nothing on stdout
+When it prints a directory, reuse that run instead of starting another. Before
+calling the scheduler, reload its plan, decisions and standing orders. Refresh the
+source requirements as described under [issue-tree sync](task-plan.md#issue-tree-sync)
+and resolve the recorded target to its current exact SHA. Apply
+[assessment reuse](exploration.md#reuse-first) against those inputs.
+
+If assessment was interrupted, findings are incomplete, or affected requirements or
+target evidence changed, complete step 4 and rerun step 5 for those units before
+scheduling them. Finish any outstanding step 6 approval once; preserve choices
+already approved. A saved size stop remains held until reassessment clears it or
+its `runWhole` recommendation is accepted. Do not treat a scheduler action as proof
+that assessment or approval finished.
+
+Then resume with `next-actions.mjs --run <dir> --resume` and
+[fresh capacity](implementation.md#live-capacity); its plan picks up whatever the
+tree gained since. The run finder exits 0 whether or not it found a run: no run prints nothing on stdout
 (`--json`: `{"found":false}`). Example: `/rush-issues #12` finds the run whose saved tree holds
 #12 and resumes it, never a second run beside it.
 
@@ -28,7 +40,7 @@ The script exits 0 whenever it ran (2 if it could not); read `outcome` in its JS
 
 - **`ready`:** continue. An open issue is work, whatever its sub-issues
   say: each `rollups` entry (open, every sub-issue closed) is a unit; the
-  explorer records what is left, or that nothing is, and then the handback
+  assessment records what is left, or that nothing is, and then the handback
   says "close #N". Example: held #40's filed prerequisite #41 closed;
   #40 is a rollup and stays a unit.
 - **`unlabeled`:** continue as on `ready`, and record the `missing` issues for
@@ -78,9 +90,11 @@ posts them; they join this run's end-of-run review
 
 ## 1. Model slots
 
-Write this turn's host evidence to a temporary JSON file and run the fast path
-([shared-modules.md](shared-modules.md#model-slots)); record its fills by exact id
-and effort. The skill names the roles — implementer, explorer, diagnoser,
+Follow [model slots](shared-modules.md#model-slots): on Pi, inspect the live native
+catalog first after checking task overrides and authoritative host preferences;
+use the portable resolver when native role resolution is unavailable or cannot
+validate either exact request. Record the actual fills by
+exact id and effort. The skill names the roles — implementer, explorer, diagnoser,
 reviewer — and the harness agent catalog chooses the models, so rank nothing and
 copy nothing from a ladder. The fills are run metadata: show each role's model
 and effort on the board and never ask which model should implement. A model the
@@ -92,14 +106,23 @@ add the repository's deterministic domain checks and review depth, never change
 the workflow or re-choose the model.
 
 Pass a pinned implementer (`implementer=<id[@effort]>` in the invocation) as
-`--implementer`. Any `ok: false` result ends the run at preflight with its `code`
-and `reason`, starting nothing: `pinned-implementer-unavailable` means the pinned
-model is unavailable and no other implementer is substituted, and
-`catalog-unavailable` or `capabilities-missing` means this host cannot resolve
-roles yet. Never revive the old picker or reuse an earlier run's pick.
+`--implementer` on the portable path. A declined result stops preflight with its
+`code` and `reason`, starting nothing: `pinned-implementer-unavailable` means the
+pinned model is unavailable and no other implementer is substituted;
+`catalog-unavailable` means the portable resolver could not be invoked.
+`capabilities-missing` means its input lacks model evidence: repair an omitted
+field from current host evidence and retry, or report precisely what could not
+be obtained. It does not establish a missing harness capability. Never revive
+the old picker or reuse an earlier run's pick.
 Example: `/rush-issues 1aboveio/ai#1545 implementer=gpt-6-luna@high` on a host
 whose catalog does not offer `gpt-6-luna` stops at preflight and starts nothing.
 
+**Catalog limitation:** optional exploration skips the worker, not catalog
+resolution. Both paths still require all four fills, including
+the explorer, even for coordinator-only assessment. Report a missing explorer as
+a catalog block; do not extract other fills from a declined response or substitute
+a model. Explorer-independent resolution needs a supported upstream protocol.
+
 ## 2. Provisional target
 
 Fetch remote heads; record the default branch as `targetBranch`.
@@ -118,11 +141,13 @@ Example: epic #12's #20 (signed release and go/no-go) and #21
 (physical acceptance) stay out of the plan; the run ends when its code units
 land instead of waiting on them.
 
-## 4. Explore
+## 4. Assess the plan
 
-Run [exploration.md](exploration.md) on the provisional target, with any
-prior findings for the same spec. On tool failures or a size-check `exploration-unfinished` verdict,
-continue the explorer with the errors. Add the links the findings show.
+Follow [exploration.md](exploration.md#choose-the-owner) on the provisional
+target, reusing prior findings for the same spec. Write findings yourself for
+clear work; delegate concrete planning unknowns to an optional explorer.
+On tool failures or `exploration-unfinished`, complete the affected findings
+using the same owner routing. Add the links the findings show.
 
 ## 5. Size check
 
@@ -154,7 +179,7 @@ by row 1 of [Never block on the human](#never-block-on-the-human).
 | `ok`, `warn` | Continue |
 | `hold` | Hold the `held` units (their dependents wait, not started); start the `runnable` units |
 | `stop` | Run-wide failure or every unit held; draft the held units' splits |
-| `exploration-unfinished` | Continue the explorer with the error |
+| `exploration-unfinished` | Complete the findings using step 4's owner routing |
 | exit 2 | Fix the plan or command |
 
 Only scope and open questions hold a unit; proof only warns. Add each
@@ -285,7 +310,7 @@ Example: `/resolve-issues` answered "run the rest" files nothing;
    prerequisites keeps its unit, now depending on them.
    Example: #30 splits into #50 and #51, so the sync adds both, drops 30,
    and unit 34, `blocked_by` #30, now waits on 50 and 51.
-4. Continue the explorer for the new units only; rerun the size check.
+4. Assess the new units only using step 4's owner routing; rerun the size check.
 5. Split a still-held slice again only while splitting makes progress: its
    largest slice is smaller than the one before.
    Example: a 7,287-line unit split into 3,455 and 2,150 lines; a held
@@ -348,16 +373,16 @@ in one interaction, with the native single-choice tool when there is one:
 
 Record each answer in `decisions`, then:
 
-- New target: fetch it, continue the explorer to recheck the findings, rerun
+- New target: fetch it, reassess affected findings using step 4's owner routing, rerun
   the size check; ask again only if it worsens to `hold` or `stop`.
-- Trim: drop the scope, continue the explorer to remove its questions and
+- Trim: drop the scope, remove its findings, questions and
   handback items, rerun the size check.
 - File the splits: follow [File a split](#file-a-split); ask again only if
   the size check returns `stop`.
 - Move to later: mark the units `blocked` (`blockedReason: human-decision`, `humanItem: 1`, the human's words as `humanNeed`); they stay in
   this run's plan and resume with it (one run per spec). Never start a
   separate follow-up run for the same spec.
-- Answer: record it, continue the explorer to set the question
+- Answer: record it, set the question
   `resolved: true`, rerun the size check.
 - Run the rest: mark held units `blocked` (`blockedReason: size-hold`) with the split path;
   their dependents stay not started (`pending`).

package/skills/engineering/resolve-issues/references/review.md

@@ -11,7 +11,8 @@ restate its rules in the brief beyond the two below.
 - Reviewer model: a different id from the implementer's
   ([preflight.md](preflight.md#1-model-slots)). Launch the reviewer with the
   plan's recorded reviewer fill — its `launch`, `instructions`, `selection` and
-  `catalogDigest` ([task-plan.md](task-plan.md#worker-selection-on-resume)) — as
+  native `catalogRevision` or portable `catalogDigest`
+  ([task-plan.md](task-plan.md#worker-selection-on-resume)) — as
   structured launch arguments, never as brief text and never a model id
   hardcoded here. On Pi that `launch` is what the live role resolver receives,
   `{ role }` unless an explicit task override or this host's own preference