@1aboveio/skills 1.0.6 → 1.0.8

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

@@ -369,7 +369,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "d65c7b826e914a41cad50c3a6cc5e9d4cefc866d0bdcce59c1f9b1bb4aebb0e1",
+      "contentDigest": "a37292865bf496db5c900602b3a2fefb87b5ebc9e6e7a185e2c8471d498c9a38",
       "digestExcludes": []
     },
     {
@@ -382,7 +382,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "b9d18cd12a60d8ff020b044f531f5639f9b6879f1b3e0a76103b7b8a0c693a57",
+      "contentDigest": "76e79c091a20274fc7a11296e5dbb2bb128525499596129baae4a11179ef7f71",
       "digestExcludes": []
     },
     {
@@ -395,7 +395,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "d7d4e683cf21c1e3621b556119b9e672b196ff7989e88595c96c5a78cb57109e",
+      "contentDigest": "e4c79b9b236babd8413778b57b67e157edc81b7870302ac38153ebd15eca6b66",
       "digestExcludes": []
     },
     {
@@ -408,7 +408,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "4b9b0dca2444536ea9d8c7d2ee6e6db348fe147c6aae0c6fc933637337f2a968",
+      "contentDigest": "c91d1d12fb3110f42779c00aa7666a7f9401bae04e63c681034c84276adab222",
       "digestExcludes": []
     },
     {
@@ -421,7 +421,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "9bc115fa42ebaf5b49af5a584c95f96f462fe08e2424caecb47e62c447133da4",
+      "contentDigest": "800748e040c2c47a78b65713fd88d1586206feb7f5a5ce052da051a72cc82743",
       "digestExcludes": []
     },
     {
@@ -434,7 +434,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "3daebcc2774b2966056f2bc195500238fdba0f50e21b0c1f601ab132241c2ee8",
+      "contentDigest": "5441c5a8c40c27c1455001ee65b5cf055d25932963410b852d6fd7753e03c7e0",
       "digestExcludes": []
     },
     {
@@ -447,7 +447,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "0828c5155448dd305514ae03d729fe8b577534445942c987e4167a15761fb1ce",
+      "contentDigest": "22b2d51f863c5e215dda1036ada423d65873652d05aee4efa83ff4e4995dfc2d",
       "digestExcludes": []
     },
     {
@@ -460,7 +460,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "385de0e4939da08010dbbee47885ef879fcee0cb4250aaf1a2ab54a07eb946a1",
+      "contentDigest": "f293e919a756e073894e959f25d874d69ef94839ccd98a92aa5073308f18f643",
       "digestExcludes": []
     },
     {
@@ -473,7 +473,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "c00da90463937b7f55441099249a710595ae75442b35ae9b5d2fcb7138aaae39",
+      "contentDigest": "3d9dd1501f80995d27026e1b7ba9751e2e10f4db7f1a427c36bd1f9eec24fcdf",
       "digestExcludes": []
     },
     {
@@ -486,7 +486,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "37329daa68b188d22f6b852a15b7eaeba5a5d55d5507be71f42ee3ff27b9cbd7",
+      "contentDigest": "4d5e6c1570bb2395813382991aa04437b60b7f20fd54234d07a7af5dbd2b31e3",
       "digestExcludes": []
     },
     {
@@ -499,7 +499,7 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "a8289f4124a0ca1aadabb9c32d800fca229f5741d96612f3d6aae2fba2dea128",
+      "contentDigest": "8d32ffe5807e680193e4ee05d51a7c6691e25ffea54bd657405e1025e318cf09",
       "digestExcludes": []
     },
     {
@@ -512,13 +512,13 @@
         "repository": "1aboveio/ai",
         "revision": "main"
       },
-      "contentDigest": "c2bbe29c38e21c1944dee77032a26823b2d3deb935b64024eb5179611e6eb121",
+      "contentDigest": "6fcf7271652b12f8a64e03cdce85fdeee10cc8456f89ac1b39631281e2e52615",
       "digestExcludes": [
         "coherence/workflow.json"
       ]
     }
   ],
-  "releaseIdentity": "321b0da7bd6d9c65417863048fdef2183a0aa2b87a569c12ceaab0b09fcac600",
+  "releaseIdentity": "0e956b77698da11b37a94d960a5f7a7102af5b761b788f1fe52a6c9716cf132d",
   "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: 0.42.1
+release-version: 0.43.1
 ---
 **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: 0.42.1
+release-version: 0.43.1
 ---
 **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: 0.42.1
+release-version: 0.43.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Harness Runtime

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

@@ -8,7 +8,7 @@ dependencies:
   - better-review
   - golden-path
   - harness-runtime
-release-version: 0.42.1
+release-version: 0.43.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Resolve issues
@@ -78,7 +78,7 @@ ships sooner at the same bar.
 `/rush-issues` runs this workflow with every answer defaulted ([shortcut mode](references/preflight.md#shortcut-mode)).
 
 **Bounds:** the harness times and stops workers · retry while cycles reach new lows; 2 without one,
-then [expire.md](references/expire.md) (a fix cycle progresses only on a new low; a resume, when it adds work the PR needs; diagnostics and records never) · workers within [live host capacity](references/implementation.md#live-capacity), one local emulator, queued for device-only work
+then [expire.md](references/expire.md) (fixes and resumes progress through verified checkpoint advances or fewer established failures; added work, diagnostics and records alone do not reset counts) · workers within [live host capacity](references/implementation.md#live-capacity), one local emulator, queued for device-only work
 and non-CI emulator proof ([scheduling](references/implementation.md#scheduling); CI confirms, never debugs) · one PR per issue · every runnable unit in one run, in dependency order · blocking review hands back
 after 2 fix rounds without a new low of open P0/P1 path rows; no fixed round cap.
 
@@ -150,26 +150,17 @@ Read each procedure right before its stage; never substitute your own.
   steps are only the read-only warehouse canary (never blocks) and the isolated, run-owned resources
   [preflight.md](references/preflight.md#never-block-on-the-human) allows.
 
+## Delivery progress
+
+Before briefing or continuing a unit, read [delivery-progress.md](references/delivery-progress.md).
+Keep one existing acceptance checkpoint per unit, preserve failure history, justify new
+infrastructure, and report verified behavior. Full acceptance and required CI still apply.
+
 ## Every brief contains
 
-- the source and criteria, as a file already in the run directory
-- the plan's `standingOrders`, verbatim, and the decisions that answer this unit's questions
-- absolute run, workspace, and findings paths; for implementers, the unit's
-  findings entry and its parents' `contracts`
-- model id, effort, and a required read-back
-- an absolute skill path when the stage invokes a leaf skill; for validating, the unit's `proof.suite` `skill` (read it first) and `local`, when set
-- the outcome and validation, with no prescribed method or evidence format
-- the [Goal](#goal) and [Principles](#principles), verbatim (a reviewer gets review.md's two rules instead)
-- the result path, `<run>/results/<unit>-<label>.json` (`<label>`: kind and attempt, e.g. `fix-2`), with `unit` and `decisionNeeded` (null or a choice)
-- at the deadline: stop starting work, commit, and report
-- environment rules: write only inside the workspace (and the findings directory for the explorer),
-  with tool caches and temp files there (`TMPDIR`, `npm_config_cache`, `UV_CACHE_DIR`); use the machine's
-  installed JDK, Android SDK, system images, and browsers (`JAVA_HOME`, `ANDROID_HOME`) where they fit,
-  or the repo's pinned Playwright image where the runner has no browser (`github-actions` runners.md);
-  edit with the harness's tools, never a shell `apply_patch`
-
-Treat a missing or unreadable result as an incomplete stage: resume a dead
-spawn once in the same workspace, never with a success claim.
+Use the full [brief checklist](references/delivery-progress.md#every-brief-contains),
+including the Goal and Principles verbatim, checkpoint history and result contract.
+Treat a missing or unreadable result as incomplete; resume a dead spawn once in its workspace.
 
 ## Workflow
 

package/skills/engineering/resolve-issues/references/delivery-progress.md

@@ -0,0 +1,63 @@
+# Delivery progress
+
+For each active unit, name **one immediate acceptance checkpoint** from its existing
+criteria: the next observable behavior or contract to prove. A narrow checkpoint guides
+the next action; it does not replace the unit's full acceptance or required CI. Independent
+units keep their own checkpoints and continue in parallel within actual resource limits.
+
+- **Preserve an existing working baseline.** Keep its source/artifact identity, relevant
+  environment and passing result as a comparison. Reuse it while those inputs remain
+  valid; do not create a new baseline campaign when none exists or treat an old artifact
+  as acceptance of the candidate. Keep only what the repo's ownership/retention rules allow.
+- **Debug the smallest failing behavior first.** Name the failing command and the
+  observation that would distinguish the remaining causes. Run the relevant host,
+  integration or device check before another broad acceptance cycle. After a correction,
+  run affected checks and the required delivery checks, not extra assurance work.
+- **Justify infrastructure before adding it.** State which existing criterion requires
+  it, why the current path cannot provide that proof, and the smallest alternative.
+  Record the choice in the existing decision/note, within current authorization. Routine
+  choices need no new approval; shared-resource changes and changes to the acceptance
+  bar retain their existing authorization rules. A failed screen alone does not justify
+  a new service, transport layer or test platform.
+- **Continue on evidence, not activity.** A handoff identifies what changed at the
+  checkpoint: a reproduction, a discriminating observation, a verified correction or
+  a concrete blocker, and the next test. A new worker, commit, diagnostic helper, test
+  count or green unrelated check is not delivery progress. Useful diagnostic evidence
+  can justify a bounded experiment; it does not reset acceptance/non-convergence counts.
+- **Reassess repeated failure at the same checkpoint.** Carry prior evidence and
+  no-progress history across worker/model changes and new infrastructure. Follow
+  [expiry](expire.md); do not restart the same approach with a fresh brief or
+  count newly invented setup milestones as progress. Replan around a smaller case or a
+  different distinguishing test, keeping the original criteria and truthful blockers.
+- **Report delivered behavior first.** Use existing plan notes/results to state criteria
+  completed and the current checkpoint. When available, include time to reproduction,
+  time to verified correction and full CI runs spent on this change. Do not invent
+  missing timings or create a separate reporting system to collect them.
+
+These rules apply to briefs and coordinator decisions; they add no plan schema, check,
+issue or automatic scheduler gate. They do not waive required validation.
+
+## Every brief contains
+
+- the source and criteria, as a file already in the run directory
+- the plan's `standingOrders`, verbatim, and the decisions that answer this unit's questions
+- absolute run, workspace, and findings paths; for implementers, the unit's
+  findings entry and its parents' `contracts`
+- model id, effort, and a required read-back
+- an absolute skill path when the stage invokes a leaf skill; for validating, the unit's `proof.suite` `skill` (read it first) and `local`, when set
+- the outcome and validation, with no prescribed method or evidence format
+- the [immediate acceptance checkpoint](#delivery-progress), existing baseline (or none),
+  and, for a continuation, the last result, remaining uncertainty and next distinguishing
+  test; retain the same checkpoint/history when changing workers
+- the [Goal](../SKILL.md#goal) and [Principles](../SKILL.md#principles), verbatim (a reviewer gets review.md's two rules instead)
+- the result path, `<run>/results/<unit>-<label>.json` (`<label>`: kind and attempt, e.g. `fix-2`), with `unit` and `decisionNeeded` (null or a choice)
+- at the deadline: stop starting work, commit, and report
+- environment rules: write only inside the workspace (and the findings directory for the explorer),
+  with tool caches and temp files there (`TMPDIR`, `npm_config_cache`, `UV_CACHE_DIR`); use the machine's
+  installed JDK, Android SDK, system images, and browsers (`JAVA_HOME`, `ANDROID_HOME`) where they fit,
+  or the repo's pinned Playwright image where the runner has no browser (`github-actions` runners.md);
+  edit with the harness's tools, never a shell `apply_patch`
+
+Treat a missing or unreadable result as an incomplete stage: resume a dead
+spawn once in the same workspace, never with a success claim.
+

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

@@ -9,10 +9,12 @@ commit alone is not progress. Lows only fall, so the loop always ends.
 Example: CI fails 5 tests, then 3, then 3, then 3: expire after the fourth
 cycle. 3, 2, 3, 2 expires too: the second 2 is no new low. 5, 4, 3, 2, 1
 never expires. A failing journey run, local or dispatched, counts as one
-failing check, so count its furthest checkpoint instead (the last step its
-log reports passing): login, store, charge, charge, charge expires;
-login, store, charge, receipt keeps going. Checkpoints are finite, so this
-loop ends too.
+failing check, so count its furthest **existing acceptance checkpoint** instead
+(the last relevant step its log reports passing): login, store, charge, charge,
+charge expires; login, store, charge, receipt keeps going. Extra instrumentation,
+new infrastructure milestones or renaming a checkpoint do not extend this sequence.
+Carry the comparison history across worker/model changes and retries; a genuinely
+changed requirement needs an explicit scope decision, not an implicit reset.
 
 | Scope | Count that must reach a new low | Expire after |
 |---|---|---|
@@ -21,9 +23,17 @@ loop ends too.
 | Warehouse canary | distinct errors | 2 attempts without progress; record a follow-up, never block |
 | Review | open P0/P1 path rows | `review-verdict.mjs` verdict `handback` ([review.md](review.md#fix-loop)) |
 | CI and merge | failing checks and tests; a failing journey run (local or `gh workflow run`) is one check, so it progresses when it passes a checkpoint no earlier run of the attempt passed | 2 fix-and-watch cycles without progress |
-| Any worker the harness reports stuck, late, or at its ceiling | none: a resume [progresses](#retry-by-failure-mode) when it adds work the unit's PR needs (product code, tests, CI config, a fix of what blocks it) or meets another acceptance criterion; diagnostics and records alone are not progress | 2 resumes in a row that add neither |
+| Any worker the harness reports stuck, late, or at its ceiling | a resume progresses when its verified result advances the existing checkpoint or reduces the established failure count; added product/test/CI code without that result is not progress, and diagnostics alone do not reset the count | 2 resumes in a row without such progress |
 
-Leave timing to the harness; never stop a worker still making progress.
+Use [Delivery progress](../SKILL.md#delivery-progress) to choose the next bounded
+experiment before applying this ladder. Reproducing a failure or collecting a missing
+observation can be useful without advancing acceptance. Record that distinction; do
+not count logs, helper code or a changed worker as a new low. On repeated non-convergence,
+reassess the approach and preserve unpassed criteria rather than creating another setup
+chain. Existing retry/block/replan rules below still apply.
+
+Leave timing to the harness for worker lifetimes. Bound individual test/subprocess waits
+explicitly with cleanup time; an outstanding tool call or heartbeat is not progress.
 
 ### Retry by failure mode
 
@@ -102,8 +112,9 @@ hours.
   wakes the run at the printed time.
 - `check-worker` means the worker changed no workspace file for
   `--quiet-minutes` (45 by default): read its latest output. Stuck: stop it
-  and take the `timeout-task` response. Still working (a long test run with
-  live output): let it run.
+  and take the `timeout-task` response. A long test with advancing test/phase results
+  inside its declared command deadline may continue. Repeated heartbeats, unchanged
+  logs or an unbounded child wait are not that evidence.
 - A watcher that ends with nothing new (a queue `STALLED` with no failing
   check) is a wait: restart it and report it in one line, or not at all.
 
@@ -202,14 +213,14 @@ logs, and record one line, with the reason code, in the unit's plan row.
 
 | Failure | Response |
 |---|---|
-| `timeout-task` or `spawn-death` | Resume in the kept workspace: commit what is there, then finish or report. Keep resuming while each resume makes [progress](#retry-by-failure-mode); after 2 in a row that add nothing, mark the unit `blocked` (`blockedReason: timeout-task` or `spawn-death`) and hand it back. A result with `decisionNeeded` is decided first ([Decide before you defer](#decide-before-you-defer)), and the resume that carries the decision always runs. Example: a fix worker loses its model stream twice but committed a fixture each time; start a third continuation. |
+| `timeout-task` or `spawn-death` | Resume in the kept workspace: commit what is there, then finish or report. Keep resuming while each resume makes [progress](#retry-by-failure-mode); after 2 in a row without verified checkpoint/failure-count progress, mark the unit `blocked` (`blockedReason: timeout-task` or `spawn-death`) and hand it back. A result with `decisionNeeded` is decided first ([Decide before you defer](#decide-before-you-defer)), and the resume that carries the decision always runs. Example: a fix worker loses its model stream after its focused regression passes; resume the remaining work with that result. Two resumes that only add fixtures without advancing the existing checkpoint trigger reassessment. |
 | Environment or infrastructure (a check cannot run: cache, emulator, runner, network, credentials) | See [Infrastructure failures](#infrastructure-failures). |
 | Implement: a fix cycle without progress | Resume with the failing command and its output as the only target, using the escalation model. 2 cycles in a row without progress: `blocked` (`blockedReason: retry-implement`), deferred on its issue. |
 | Review: `review-verdict.mjs` verdict `fix` | Follow its `action` ([review.md](review.md#fix-loop)). |
 | Review: `review-verdict.mjs` verdict `handback` (`not-converging`) | Stop fixing; mark the unit `blocked` (`blockedReason: review-handback`) and defer the PR with its open findings on its issue. |
 | Review: `review-verdict.mjs` verdict `decide`, or a worker's `decisionNeeded` | [Decide before you defer](#decide-before-you-defer). |
 | CI: a fix cycle without progress | Treat the failing check as the failing test: the next fix worker runs on the escalation model with that check as its only target. 2 cycles in a row without progress: `blocked` (`blockedReason: retry-ci`), deferred on its issue. |
-| Too big for one attempt | Resume in the kept workspace while each resume makes [progress](#retry-by-failure-mode); after 2 in a row that make none, draft a split in `<run>/splits/`, file it into the spec's tree, and run the slices the sync adds ([preflight.md](preflight.md#put-every-filed-issue-in-the-tree)). |
+| Too big for one attempt | Resume in the kept workspace while each resume makes [progress](#retry-by-failure-mode); after 2 in a row without verified checkpoint/failure-count progress, draft a split in `<run>/splits/`, file it into the spec's tree, and run the slices the sync adds ([preflight.md](preflight.md#put-every-filed-issue-in-the-tree)). |
 | A required proof the unit has no environment for yet | The unit builds it; see [Proof stays with its unit](#proof-stays-with-its-unit). |
 | Dependency | Fix the edge; resume when runnable. |
 | A capability the unit needs is missing and no unit builds it (a shared driver, fixture, or hook) | Build it inside the first unit that needs it; units that need it later get `dependsOn` on that unit. Only when that puts the unit past the size check's line limit, file it as its own issue beside them, with `blocked_by` on the units that use it, never on their parent issue. Example: three proof units each need a device-state reader: the first builds it, the other two depend on the first. |
@@ -229,7 +240,9 @@ dependents start while the parent still proves itself; only the unit's own
 merge waits for its proof.
 
 - **No working suite or environment yet? The unit builds what its proof
-  needs**, with access the run already has (the run's local emulator, when
+  needs**, after recording why the existing path cannot prove that criterion and why
+  the proposed addition is the smallest suitable option ([Delivery progress](../SKILL.md#delivery-progress)),
+  with access the run already has (the run's local emulator, when
   [its queue](implementation.md#scheduling) hands it over, a
   disposable database, a container, a tunnel hostname), counted in its
   lines like a missing prerequisite. When two or more units need the same

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

@@ -59,6 +59,12 @@ boundary, workspace, outcome, validation, and return contract; prescribe no
 method or evidence format. Name a leaf skill only as the findings record it
 (`proof.suite.skill`, with `local`).
 
+A continuation inherits the immediate acceptance checkpoint and history from
+[Delivery progress](../SKILL.md#delivery-progress). In its existing result, state what
+new evidence changes the next action; if nothing changed, say so instead of relaunching
+the same work. A passing setup check is not a substitute for the blocked behavior.
+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
 human-only proof. Report each question in the result's `decisionNeeded`
@@ -87,7 +93,9 @@ implementer in its kept workspace with the brief and its findings entry.
    options, recommendation; options are ways to proceed, and staying
    blocked is never one). Fix workers write the same file. Return
    nothing else: no artifact hashes, version inventories, screenshots,
-   copied logs, or earlier attempts.
+   copied logs, or earlier attempts. For a continuation, include the current checkpoint,
+   outcome and relevant prior-result links in the existing integration notes; do not
+   duplicate the full attempt history.
 
 After 2 fix cycles without progress, or a stuck or late worker, follow
 [expire.md](expire.md). Start the next worker in the same workspace with the

package/skills/engineering/resolve-issues/references/task-plan.md

@@ -85,7 +85,7 @@ Fleet `status`: `pending`, `in-flight`, `succeeded`, `failed`,
 | `workerKind` | `implement`, `fix`, or `review`, set with `worker`; the [live-capacity scheduler](implementation.md#live-capacity) (`next-actions.mjs`) prints `worker-kind` for any other kind or none. An infrastructure diagnosis or a test-first worker is a `fix` worker. The explorer is the `explore` fleet row's worker, never a unit's; a merge-queue watcher is not a worker |
 | `estimatedLines` | Explorer estimate |
 | `sizeCheck` | Measures, `verdict` (the size check's per-unit verdict; `stop` means held), scope and proof verdicts, split or verification path; `runWhole: true` once a recommendation to run a held unit whole is accepted |
-| `note` | SHA, expiry reason code, failure and the response taken, or blocker |
+| `note` | SHA, expiry reason code, failure and response, or blocker; for active debugging, the immediate acceptance checkpoint, baseline/result link and next distinguishing test ([delivery progress](../SKILL.md#delivery-progress)) |
 | `pr`, `headSha`, `reviewedHead` | PR URL, current HEAD (recorded from the implementer's first pushed commit on, so the draft PR opens early), last HEAD whose verdict was `pass` (reviewed or carried) |
 | `delivery` | `building`, `opening`, `review`, `ci`, `merged`, `blocked` |
 | `reviewRound`, `fixRound` | Review-attempt/file number, and the count of blocking-fix cycles (a record, not a cap); record both from the review/verdict, never charge skips, or reviews that follow a passing one, as fixes |
@@ -259,6 +259,9 @@ changes, unit outcomes, validation turning red or green, canary events,
 retries and escalations, newly runnable dependencies, PR open, HEAD change, or
 merge, and about every 5 minutes; skip when nothing changed.
 
-Final board: each unit's outcome with its scope and proof verdicts, every PR URL, SHA,
-and merge state, retry and escalation totals, each blocker, and the exploration
-path.
+Final board: lead with behavior delivered and criteria still unproved, then each unit's
+scope and proof verdicts, PR URL, SHA, merge state, retries, blocker and exploration path.
+Use existing result timestamps and CI records, when available, for time to reproduction,
+time to verified correction and full CI runs per delivered change. Mark missing data as
+unknown. Worker/test counts describe activity, not acceptance; do not add a reporting
+pipeline or duplicate the plan to produce these summaries.

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

@@ -4,7 +4,7 @@ description: "Slash/explicit-only (/resolve-release). Full GitHub Flow release f
 disable-model-invocation: true
 metadata:
   workflow-role: coordinator
-release-version: 0.42.1
+release-version: 0.43.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Resolve release

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

@@ -6,7 +6,7 @@ metadata:
   workflow-role: coordinator
 dependencies:
   - resolve-issues
-release-version: 0.42.1
+release-version: 0.43.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Rush issues (shortcut of resolve-issues)
@@ -50,7 +50,10 @@ question.
      and complete the goal
      ([done.md](../resolve-issues/references/done.md#close-the-run)).
 3. Everything else — run rules, stages, scripts, review, CI and merge, and the
-   done criteria — applies exactly as `resolve-issues` states it.
+   done criteria — applies exactly as `resolve-issues` states it. In particular,
+   [Delivery progress](../resolve-issues/SKILL.md#delivery-progress) applies in shortcut
+   mode too: keep one immediate checkpoint per active unit, justify infrastructure and
+   reassess repeated non-convergence. More worker activity is not a reason to reset it.
    The shared [task-plan checkpoints](../resolve-issues/references/task-plan.md#checkpoints)
    apply too: on Pi, bind or reload through `update_plan` with the absolute
    workflow path and persisted revision (no event means read-only), then

package/skills/engineering/rush-release/SKILL.md

@@ -6,7 +6,7 @@ metadata:
   workflow-role: coordinator
 dependencies:
   - resolve-release
-release-version: 0.42.1
+release-version: 0.43.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Rush release (shortcut of resolve-release)

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

@@ -1,7 +1,7 @@
 ---
 name: test-quality
 description: "Seven principles for tests that catch real bugs, and an audit that reports weak, redundant, and not-coverage tests without fixing them. Use when writing, changing, or reviewing tests, or when asked whether tests are useful, redundant, over-mocked, flaky, only assert static text, or test config files, or asked to make a slow test suite faster without losing coverage, or when the user asks to write the testing conventions into a repo's CONTRIBUTING.md. NOT defining what a spec must prove (ensure-coverage) or authoring browser tests (e2e-test)."
-release-version: 0.42.1
+release-version: 0.43.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Test Quality

package/skills/risk-compliance/compliance-audit/SKILL.md

@@ -2,7 +2,7 @@
 name: compliance-audit
 version: 2.9.0
 description: "Audit operations against financial-compliance checklists (AML/KYC, VARS, PCI-DSS, TPA oversight, onboarding, transaction monitoring). Produces tracker.md (with a tracker.xlsx export) and phase-trail.md with layered validation; cites evidence by original filename. Input: reg-parser or the built-in VARS checklist."
-release-version: 0.42.1
+release-version: 0.43.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Compliance Audit

package/skills/risk-compliance/contract-compare/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: contract-compare
 description: "Compare two or more contracts side-by-side for structured diff, gap analysis, and benchmarking. Use when: comparing contracts or agreements, contract diff, compare terms, vendor-vs-vendor, compare our template vs theirs, compliance gap between contracts. NOT for single-contract risk review — use contract-review for that."
-release-version: 0.42.1
+release-version: 0.43.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Contract Compare

package/skills/risk-compliance/contract-review/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: contract-review
 description: "Review contracts for legal, commercial, and compliance risks via convert → chunk review → merge → validate (+ optional mandate preprocessing). Use for reviewing, auditing, or checking any contract, agreement, NDA, MSA, or SLA; input a file path (PDF/DOCX/TXT) or pasted text."
-release-version: 0.42.1
+release-version: 0.43.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Contract Review

package/skills/risk-compliance/doc-authenticity/SKILL.md

@@ -3,7 +3,7 @@ name: doc-authenticity
 version: 0.4.1
 description: "Screen PDF documents and raster images for fabrication, tampering, Photoshop or other image-editor use, and content validity. Detects file type, runs format-specific authenticity forensics, classifies bank statements, conversation logs, invoices, agreements, and other documents, then applies type-specific validity checks. Produces separate authenticity (NO_EVIDENCE_OF_MODIFICATION / SUSPICIOUS / LIKELY_MODIFIED / INCONCLUSIVE) and validity (VALID / INVALID / INCONCLUSIVE) verdicts. Use whenever a user asks whether a document, screenshot, scan, statement, invoice, contract, chat log, receipt, or payment evidence is genuine, original, edited, Photoshopped, manipulated, fake, or valid."
 disable-model-invocation: true
-release-version: 0.42.1
+release-version: 0.43.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Document and Image Authenticity

package/skills/risk-compliance/fraud-analysis/SKILL.md

@@ -10,7 +10,7 @@ description: >
   impact, and a business report. Use for fraud, scam, mule, account-takeover,
   chargeback, dispute, transfer, collection, or payout risk analysis even when the
   user does not name this skill.
-release-version: 0.42.1
+release-version: 0.43.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Fraud Analysis

package/skills/risk-compliance/payment-analysis/SKILL.md

@@ -14,7 +14,7 @@ description: >
   transactions" — even if they do not say payment-analysis. Do NOT use for
   supervised fraud-rule mining (fraud-analysis) or TLD / MCC-miscoding
   clusters (tld-detection).
-release-version: 0.42.1
+release-version: 0.43.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Payment Analysis

package/skills/risk-compliance/similar-domain/SKILL.md

@@ -8,7 +8,7 @@ description: >
   links, an entity chain, and a watchlist for the operator's next domains.
   Not transaction data (tld-detection) or fraud rules (fraud-analysis).
 disable-model-invocation: true
-release-version: 0.42.1
+release-version: 0.43.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # Similar Domain

package/skills/risk-compliance/tld-detection/SKILL.md

@@ -11,7 +11,7 @@ description: >
   with a ≤3-sentence summary.
   Not payment-analysis, fraud-analysis, or website research (similar-domain).
 disable-model-invocation: true
-release-version: 0.42.1
+release-version: 0.43.1
 ---
 **Updates:** Once/session run `node <skill-base-dir>/release-check.mjs`.
 # TLD Detection