@olegkoval/agent-skills 1.49.1 → 1.50.0

package/.github/prompts/codexloop.prompt.md

@@ -4,7 +4,7 @@
 description: "Iteratively drives a GitHub PR to zero unresolved OpenAI Codex review comments, verifying every finding against the real code first, fixes only the correct ones, and rebuts false positives without changing correct code."
 ---
 
-Use the olko:codexloop skill.
+Use the codexloop skill.
 
 # Codexloop
 
@@ -63,6 +63,12 @@ Switch to the PR branch if not already on it. Capture `OWNER`/`REPO` (`gh repo v
 
 ## 2. The loop (max 5 iterations)
 
+At the end of every invocation, post exactly one top-level PR conversation comment summarizing
+the result, including iterations, comments fixed, comments rebutted, and anything remaining. This
+is required even when the loop times out or reaches its iteration cap; report that state honestly.
+End the comment with: **Useful? React with 👍 / 👎.** Do not post a separate summary comment for
+each iteration.
+
 Keep an explicit iteration counter and stop at 5: the cap is a real bound to enforce, not a
 figure of speech. Each pass through A–G is one iteration; on hitting the cap, go straight to the
 report and list what is still unresolved rather than starting a sixth.
@@ -184,6 +190,10 @@ gh pr view <PR> --json headRefOid -q .headRefOid   # must match
 
 If they differ, stop: the fix is not on the PR, so nothing may be resolved yet.
 
+Every fixed Codex thread must be replied to and resolved after this push is verified. A fix is not
+complete while its thread remains unresolved. If no code changed, rebutted threads can be replied
+to and resolved without a push.
+
 ### F. Reply to and resolve every addressed thread
 
 Only now, with the fixes pushed, reply and resolve. Fetch unresolved threads, **following
@@ -220,7 +230,10 @@ gh api graphql -f query='mutation { resolveReviewThread(input: {threadId: "THREA
 ```
 
 Resolve a thread only for comments authored by `$BOT` that you have fixed or rebutted: never
-blanket-resolve, and never resolve a human reviewer's thread.
+blanket-resolve, and never resolve a human reviewer's thread. For each fixed comment, verify the
+push first, reply with the change made, then resolve the thread and verify `isResolved: true`.
+For each rebutted comment, reply with the evidence and verify resolution. Do not report a comment
+as fixed or rebutted until its thread is confirmed resolved.
 
 Threads you are **rebutting** need no push, so they may be replied to and resolved regardless of
 whether step D changed code.

package/.kiro/steering/codexloop.md

@@ -62,6 +62,12 @@ Switch to the PR branch if not already on it. Capture `OWNER`/`REPO` (`gh repo v
 
 ## 2. The loop (max 5 iterations)
 
+At the end of every invocation, post exactly one top-level PR conversation comment summarizing
+the result, including iterations, comments fixed, comments rebutted, and anything remaining. This
+is required even when the loop times out or reaches its iteration cap; report that state honestly.
+End the comment with: **Useful? React with 👍 / 👎.** Do not post a separate summary comment for
+each iteration.
+
 Keep an explicit iteration counter and stop at 5: the cap is a real bound to enforce, not a
 figure of speech. Each pass through A–G is one iteration; on hitting the cap, go straight to the
 report and list what is still unresolved rather than starting a sixth.
@@ -183,6 +189,10 @@ gh pr view <PR> --json headRefOid -q .headRefOid   # must match
 
 If they differ, stop: the fix is not on the PR, so nothing may be resolved yet.
 
+Every fixed Codex thread must be replied to and resolved after this push is verified. A fix is not
+complete while its thread remains unresolved. If no code changed, rebutted threads can be replied
+to and resolved without a push.
+
 ### F. Reply to and resolve every addressed thread
 
 Only now, with the fixes pushed, reply and resolve. Fetch unresolved threads, **following
@@ -219,7 +229,10 @@ gh api graphql -f query='mutation { resolveReviewThread(input: {threadId: "THREA
 ```
 
 Resolve a thread only for comments authored by `$BOT` that you have fixed or rebutted: never
-blanket-resolve, and never resolve a human reviewer's thread.
+blanket-resolve, and never resolve a human reviewer's thread. For each fixed comment, verify the
+push first, reply with the change made, then resolve the thread and verify `isResolved: true`.
+For each rebutted comment, reply with the evidence and verify resolution. Do not report a comment
+as fixed or rebutted until its thread is confirmed resolved.
 
 Threads you are **rebutting** need no push, so they may be replied to and resolved regardless of
 whether step D changed code.

package/.windsurf/rules/codexloop.md

@@ -61,6 +61,12 @@ Switch to the PR branch if not already on it. Capture `OWNER`/`REPO` (`gh repo v
 
 ## 2. The loop (max 5 iterations)
 
+At the end of every invocation, post exactly one top-level PR conversation comment summarizing
+the result, including iterations, comments fixed, comments rebutted, and anything remaining. This
+is required even when the loop times out or reaches its iteration cap; report that state honestly.
+End the comment with: **Useful? React with 👍 / 👎.** Do not post a separate summary comment for
+each iteration.
+
 Keep an explicit iteration counter and stop at 5: the cap is a real bound to enforce, not a
 figure of speech. Each pass through A–G is one iteration; on hitting the cap, go straight to the
 report and list what is still unresolved rather than starting a sixth.
@@ -182,6 +188,10 @@ gh pr view <PR> --json headRefOid -q .headRefOid   # must match
 
 If they differ, stop: the fix is not on the PR, so nothing may be resolved yet.
 
+Every fixed Codex thread must be replied to and resolved after this push is verified. A fix is not
+complete while its thread remains unresolved. If no code changed, rebutted threads can be replied
+to and resolved without a push.
+
 ### F. Reply to and resolve every addressed thread
 
 Only now, with the fixes pushed, reply and resolve. Fetch unresolved threads, **following
@@ -218,7 +228,10 @@ gh api graphql -f query='mutation { resolveReviewThread(input: {threadId: "THREA
 ```
 
 Resolve a thread only for comments authored by `$BOT` that you have fixed or rebutted: never
-blanket-resolve, and never resolve a human reviewer's thread.
+blanket-resolve, and never resolve a human reviewer's thread. For each fixed comment, verify the
+push first, reply with the change made, then resolve the thread and verify `isResolved: true`.
+For each rebutted comment, reply with the evidence and verify resolution. Do not report a comment
+as fixed or rebutted until its thread is confirmed resolved.
 
 Threads you are **rebutting** need no push, so they may be replied to and resolved regardless of
 whether step D changed code.

package/README.md

@@ -115,7 +115,8 @@ cd agent-skills
 ./scripts/install-codex-symlinks.sh
 ```
 
-Then mention a lookup name in a new Codex session:
+Then mention a lookup name in a new Codex session. The Codexloop skill is available directly as
+`$codexloop` (or by name in a prompt):
 
 ```text
 Use the olko:semantic-release-beta skill to add prereleases on a beta branch.

package/adapters/claude/olko-github-pr/skills/codexloop/SKILL.md

@@ -8,7 +8,7 @@ description: >
   review", "fix codex comments", "codex loop", or wants to iterate on Codex PR review feedback.
 compatibility: GitHub only (Codex code review is a GitHub app). Requires git + gh (GitHub CLI) authenticated, and the Codex / ChatGPT connector app installed on the repo with code review enabled.
 metadata:
-  version: "1.0"
+  version: "1.1"
 allowed-tools: Bash(gh:*) Bash(git:*)
 ---
 <!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
@@ -70,6 +70,12 @@ Switch to the PR branch if not already on it. Capture `OWNER`/`REPO` (`gh repo v
 
 ## 2. The loop (max 5 iterations)
 
+At the end of every invocation, post exactly one top-level PR conversation comment summarizing
+the result, including iterations, comments fixed, comments rebutted, and anything remaining. This
+is required even when the loop times out or reaches its iteration cap; report that state honestly.
+End the comment with: **Useful? React with 👍 / 👎.** Do not post a separate summary comment for
+each iteration.
+
 Keep an explicit iteration counter and stop at 5: the cap is a real bound to enforce, not a
 figure of speech. Each pass through A–G is one iteration; on hitting the cap, go straight to the
 report and list what is still unresolved rather than starting a sixth.
@@ -191,6 +197,10 @@ gh pr view <PR> --json headRefOid -q .headRefOid   # must match
 
 If they differ, stop: the fix is not on the PR, so nothing may be resolved yet.
 
+Every fixed Codex thread must be replied to and resolved after this push is verified. A fix is not
+complete while its thread remains unresolved. If no code changed, rebutted threads can be replied
+to and resolved without a push.
+
 ### F. Reply to and resolve every addressed thread
 
 Only now, with the fixes pushed, reply and resolve. Fetch unresolved threads, **following
@@ -227,7 +237,10 @@ gh api graphql -f query='mutation { resolveReviewThread(input: {threadId: "THREA
 ```
 
 Resolve a thread only for comments authored by `$BOT` that you have fixed or rebutted: never
-blanket-resolve, and never resolve a human reviewer's thread.
+blanket-resolve, and never resolve a human reviewer's thread. For each fixed comment, verify the
+push first, reply with the change made, then resolve the thread and verify `isResolved: true`.
+For each rebutted comment, reply with the evidence and verify resolution. Do not report a comment
+as fixed or rebutted until its thread is confirmed resolved.
 
 Threads you are **rebutting** need no push, so they may be replied to and resolved regardless of
 whether step D changed code.

package/adapters/claude/olko-github-pr/skills/lekker-review/SKILL.md

@@ -87,6 +87,31 @@ No nitpicking. Critical and Important findings are reserved for things that
 could cause bugs, outages, data loss, security incidents, or real performance
 problems at scale.
 
+**Boundary-first review rule:** for stateful or integration-heavy changes,
+review the complete behavioral chain rather than the changed helper alone:
+
+```text
+production entry point
+→ decision point
+→ runtime realization
+→ downstream consumer
+→ persistence/cache/cleanup owner
+```
+
+Require the review to distinguish logical identity from physical/runtime
+identity, and to test the relevant transition matrix: success, `null`, `undefined`,
+exception, retry, fallback, rotation, cache reuse/eviction, proxy parity, and
+quoted/history input where applicable. A copied helper test is isolated
+evidence, not proof that the production boundary works.
+
+Every verdict-affecting finding should carry a boundary map and an evidence
+class. The report must distinguish source inspection, isolated tests,
+repository tests, composed production-entry probes, production probes, and
+hosted CI. Never upgrade one evidence class into another in the wording.
+
+After a fix, re-run the original proof *and* audit the newly changed lifecycle
+boundary for regressions. A green reproduction is necessary, not sufficient.
+
 **HARD RULE: the `## 💰 Review Cost` block is mandatory.** Every review MUST
 end with an evidence-backed cost block and no `<N>` placeholders. Use real
 numbers for measurements the host exposes; follow `references/output-format.md`
@@ -290,7 +315,7 @@ page for this PR.
 | Review agents               | 2 triage (haiku)      | 5 specialists (sonnet) | 5 specialists (sonnet)  |
 | Per-finding verification    | Criticals + Importants | Criticals + Importants | Criticals + Importants |
 | Completeness critic         | skip                  | skip                | included                   |
-| Proof-of-bug (failing test per Critical) | skip     | included (max 5)    | included (max 5)           |
+| Proof-of-bug (failing test per Critical or composed-boundary Important) | skip     | included (max 5)    | included (max 5)           |
 | Living review artifact      | included              | included            | included                   |
 | Housekeeping (optional memory/notes writeback) | skip | included            | included                   |
 | `--post`                    | supported             | supported           | supported                  |

package/adapters/claude/olko-github-pr/skills/lekker-review/references/agents/completeness-critic.md

@@ -14,6 +14,18 @@ were declared "no findings" too quickly. For each angle:
 Be concrete: cite diff lines, not vibes. If you genuinely cannot find a missed
 angle, return "No gaps found."
 
+Always consider these maintainer-grade gaps before returning no gaps:
+- the real production entry point and downstream consumer were not exercised;
+- the selected value was not traced through runtime realization, persistence,
+  cleanup, cache reuse, or fallback;
+- logical identity was conflated with physical/runtime identity;
+- a state-transition matrix is missing for `None`, exceptions, retries,
+  rotation, proxying, or alternate transport;
+- the fix was checked only against the original symptom, not for a new defect
+  introduced at the changed ordering or lifecycle boundary;
+- the evidence is an isolated harness or local test but the review claims
+  composed behavior or hosted-CI acceptance.
+
 Agent findings:
 <AGENT_FINDINGS_SUMMARY>
 

package/adapters/claude/olko-github-pr/skills/lekker-review/references/agents/implementation.md

@@ -37,7 +37,32 @@ Axes to cover:
   sort/dedup on large arrays that could be done at DB level.
 - Integration Contracts: Shopify API misuse, BC API assumptions, webhook
   idempotency, external API pagination not handled.
-- GraphQL pagination (GQL-1): for every GraphQL query in the diff that uses a
+
+Boundary contract and lifecycle map (required for every Critical/Important
+finding involving routing, persistence, caching, fallback, proxying, or an
+external integration):
+- `entryPoint`: identify the real production trigger that reaches the changed
+  code (HTTP route, webhook, CLI command, queue consumer, gateway ingress, etc.).
+- `decisionPoint`: identify where the behavior is selected or transformed.
+- `realizationPoint`: identify where the selected behavior becomes runtime state.
+- `consumer`: identify the downstream consumer that actually relies on the
+  contract, not merely the helper that constructs it.
+- `stateOwner`: identify the durable/session/cache owner when state crosses a
+  turn, request, retry, or process boundary.
+- `identityDimensions`: list every identity that must remain distinct, such as
+  logical session key, physical session id, provider alias, resolved provider,
+  model, and API mode.
+- `transitions`: list the relevant success, `null`, `undefined`, exception, retry, fallback,
+  session-rotation, cache-reuse, and proxy/alternate-transport transitions.
+- `evidenceClass`: label the strongest evidence actually checked: `source`,
+  `isolated-test`, `repository-test`, `composed-test`, `production-probe`, or
+  `hosted-ci`. Never call an isolated harness a production-path proof.
+
+Do not report a stateful/integration finding without this boundary object. If
+the production entry point or downstream consumer cannot be identified, mark
+the claim as unverified rather than inferring behavior from a helper alone.
+
+GraphQL pagination (GQL-1): for every GraphQL query in the diff that uses a
   nodes connection (`nodes { ... }`):
   (a) Check that `pageInfo { hasNextPage endCursor }` is present alongside nodes: if missing, Critical.
   (b) Check that all pages are fetched (a loop or recursion using endCursor): a single-page fetch is a bug, Critical.

package/adapters/claude/olko-github-pr/skills/lekker-review/references/agents/prover.md

@@ -4,11 +4,18 @@
 
 ## Mission
 
-A Critical finding is an argument until someone runs it. Your job is to turn it
+A Critical finding, or an Important finding with a composed boundary map, is an
+argument until someone runs it. Your job is to turn it
 into a demonstration: write ONE test that asserts the CORRECT behavior of the
 code the finding targets, run it in the real worktree, and capture it failing
 for the exact reason the finding claims.
 
+For a finding with `boundary`, prefer entering through the recorded production
+entry point and reaching the recorded downstream consumer. Do not replace a
+composed proof with a copied helper test just because the helper is easier to
+import. If full composition is impossible, report the strongest lower evidence
+class honestly.
+
 Write the test as if the bug were already fixed. It must fail today precisely
 *because* it isn't fixed. **Never write a test that asserts the buggy behavior
 just to have something red** -- a proof that asserts wrongness is worthless and

package/adapters/claude/olko-github-pr/skills/lekker-review/references/agents/test-quality.md

@@ -128,8 +128,26 @@ g) Mock smell: test the behavior, not the way it's built
    (time, randomness, injected network failure), or a dependency that genuinely
    cannot run in the test environment. The tell for a good mock: the behavior
    under test only exists because the boundary did something (e.g. a retry
-   banner that appears only when the fetch rejects). Even then, prefer an
-   injected simple fake over a module-level spy, and assert what the user sees.
+ banner that appears only when the fetch rejects). Even then, prefer an
+ injected simple fake over a module-level spy, and assert what the user sees.
+
+ h) Composed boundary and transition coverage
+ For every stateful or integration-heavy change, do not stop at testing the
+ helper. Trace the real entry point through the decision point, runtime
+ realization, downstream consumer, and persistence/cleanup owner. Require a
+ test or explicit evidence for the relevant transition matrix:
+ - success, `None`, exception, and disabled-feature paths;
+ - retry and fallback behavior;
+ - session/request rotation and cache reuse or eviction;
+ - proxy or alternate transport parity;
+ - quoted/history input versus newly authored input;
+ - provider/model/API-mode identity when routing is involved.
+
+ A test that only asserts a helper return value is `isolated-test` evidence,
+ not `composed-test` evidence. Flag a Critical/Important finding when the
+ changed contract is consumed through a different path than the test covers,
+ or when the test can pass while the stateful consumer still receives the
+ wrong identity or ordering.
 
 Report each per-line issue as:
   `test-file:line, <concise description of the gap or weakness>`

package/adapters/claude/olko-github-pr/skills/lekker-review/references/agents/verifier.md

@@ -123,6 +123,31 @@ convention finding with no verifiable precedent does not ship.
 
 ---
 
+## Step 4b -- Boundary contract and evidence check
+
+For any Critical/Important finding involving routing, persistence, caching,
+fallback, proxying, quoted input, or an external integration, read the
+finding's `boundary` object. It should identify the real production entry
+point, decision point, runtime realization point, downstream consumer, state
+owner, and relevant identity dimensions/transitions.
+
+Reconstruct the path in `WORKTREE_PATH` from entry point to consumer. A copied
+helper test or a mock that never reaches the consumer is only isolated
+evidence. Do not confirm a verdict-affecting finding as production-path proof
+unless the claimed failure reaches the stateful consumer or the review clearly
+labels the evidence as isolated.
+
+If the finding has no boundary object or no usable production entry point or
+consumer, keep it unverified and non-blocking; drop it when the missing boundary
+is the crux of the claim. The workflow enforces this as an unverified observation
+even if a verifier confirms it. Record the strongest evidence class actually checked
+(`source`, `isolated-test`, `repository-test`, `composed-test`,
+`production-probe`, or `hosted-ci`) in the reasoning.
+
+Build a small transition matrix for the affected contract. At minimum check
+success, `null`, `undefined`, exception, retry/fallback, state rotation, cache reuse or
+eviction, and proxy/alternate transport whenever those transitions exist.
+
 ## Step 5 -- Fix validation
 
 Before confirming the finding, identify the callers and consumers of the changed

package/adapters/claude/olko-github-pr/skills/lekker-review/references/fix-mode.md

@@ -210,6 +210,29 @@ check after any revert triggered here before moving on.
 
 ---
 
+## Step 5c -- Fix delta audit
+
+After the original proof flips red → green, audit the *new* boundary created by
+the fix. Do not assume that making the original assertion pass makes the
+lifecycle safe.
+
+For each fixed Critical/Important finding involving state, routing, ordering,
+proxying, persistence, caching, fallback, or quoted input:
+
+1. Re-read the entire changed path from the production entry point to the
+   downstream consumer.
+2. Re-run the relevant transition matrix: success, `None`, exception, retry,
+   fallback, rotation, cache reuse/eviction, and alternate transport where
+   applicable.
+3. Check that logical identity, runtime identity, provider/API identity, and
+   durable identity are still distinct where the contract requires it.
+4. Add a focused regression probe when the fix moved work across an ordering or
+   lifecycle boundary. The probe must enter through the real path when feasible.
+
+If the audit finds a new failure, revert the whole group and mark it
+`failed: fix-delta-regression`. A green original proof is not sufficient to
+commit a fix that breaks a neighboring transition.
+
 ## Step 6 -- Commit (local only)
 
 One commit per file group, in group order. Stage explicitly -- never `git add -A`,

package/adapters/claude/olko-reflection/skills/agent-ops-retro/scripts/mine-transcripts.mjs

@@ -45,7 +45,6 @@ function walk(dir, out = []) {
   return out;
 }
 
-// A user-role text record that is really harness output, not something a person typed.
 // A user-role text record that is really harness output, not something a person typed.
 // Each alternative below was found by a run that mis-counted. The first pass caught the
 // obvious wrappers and still let 26% through: skill body dumps, image attachments,
@@ -62,6 +61,15 @@ const HARNESS = new RegExp('^(' + [
   '\\[Image #\\d+\\]',                    // bare attachment
   '\\[Image: source:',
   '\\[Pasted text',
+  // v3: the 2026-09-29 run found v2 still let 66% through, almost all of it these five.
+  'Another Claude session sent a message', // subagent / cross-session hand-back
+  '<agent-message',
+  'This session is being continued from a previous conversation', // compaction resume
+  'Stop hook feedback:',
+  '\\[SYSTEM NOTIFICATION',
+  'Your response above was cut off',
+  '\\(Re-invocation of /',
+  '\\[\\d+ prior /loop wakeup',
 ].join('|') + ')');
 
 const textOf = (msg) => {
@@ -261,7 +269,7 @@ if (problems.length) {
   console.error('INCONSISTENT REPORT, refusing to write:\n  ' + problems.join('\n  '));
   process.exit(3);
 }
-report.echoFilterVersion = 2;
+report.echoFilterVersion = 3;
 
 fs.writeFileSync(OUT, JSON.stringify(report, null, 1));
 fs.writeFileSync(OUT.replace(/\.json$/, '') + '-turns.json', JSON.stringify(S.humanTurns, null, 1));

package/adapters/cursor/olko-github-pr/skills/codexloop/SKILL.md

@@ -8,7 +8,7 @@ description: >
   review", "fix codex comments", "codex loop", or wants to iterate on Codex PR review feedback.
 compatibility: GitHub only (Codex code review is a GitHub app). Requires git + gh (GitHub CLI) authenticated, and the Codex / ChatGPT connector app installed on the repo with code review enabled.
 metadata:
-  version: "1.0"
+  version: "1.1"
 allowed-tools: Bash(gh:*) Bash(git:*)
 ---
 <!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
@@ -70,6 +70,12 @@ Switch to the PR branch if not already on it. Capture `OWNER`/`REPO` (`gh repo v
 
 ## 2. The loop (max 5 iterations)
 
+At the end of every invocation, post exactly one top-level PR conversation comment summarizing
+the result, including iterations, comments fixed, comments rebutted, and anything remaining. This
+is required even when the loop times out or reaches its iteration cap; report that state honestly.
+End the comment with: **Useful? React with 👍 / 👎.** Do not post a separate summary comment for
+each iteration.
+
 Keep an explicit iteration counter and stop at 5: the cap is a real bound to enforce, not a
 figure of speech. Each pass through A–G is one iteration; on hitting the cap, go straight to the
 report and list what is still unresolved rather than starting a sixth.
@@ -191,6 +197,10 @@ gh pr view <PR> --json headRefOid -q .headRefOid   # must match
 
 If they differ, stop: the fix is not on the PR, so nothing may be resolved yet.
 
+Every fixed Codex thread must be replied to and resolved after this push is verified. A fix is not
+complete while its thread remains unresolved. If no code changed, rebutted threads can be replied
+to and resolved without a push.
+
 ### F. Reply to and resolve every addressed thread
 
 Only now, with the fixes pushed, reply and resolve. Fetch unresolved threads, **following
@@ -227,7 +237,10 @@ gh api graphql -f query='mutation { resolveReviewThread(input: {threadId: "THREA
 ```
 
 Resolve a thread only for comments authored by `$BOT` that you have fixed or rebutted: never
-blanket-resolve, and never resolve a human reviewer's thread.
+blanket-resolve, and never resolve a human reviewer's thread. For each fixed comment, verify the
+push first, reply with the change made, then resolve the thread and verify `isResolved: true`.
+For each rebutted comment, reply with the evidence and verify resolution. Do not report a comment
+as fixed or rebutted until its thread is confirmed resolved.
 
 Threads you are **rebutting** need no push, so they may be replied to and resolved regardless of
 whether step D changed code.

package/adapters/cursor/olko-reflection/skills/agent-ops-retro/scripts/mine-transcripts.mjs

@@ -45,7 +45,6 @@ function walk(dir, out = []) {
   return out;
 }
 
-// A user-role text record that is really harness output, not something a person typed.
 // A user-role text record that is really harness output, not something a person typed.
 // Each alternative below was found by a run that mis-counted. The first pass caught the
 // obvious wrappers and still let 26% through: skill body dumps, image attachments,
@@ -62,6 +61,15 @@ const HARNESS = new RegExp('^(' + [
   '\\[Image #\\d+\\]',                    // bare attachment
   '\\[Image: source:',
   '\\[Pasted text',
+  // v3: the 2026-09-29 run found v2 still let 66% through, almost all of it these five.
+  'Another Claude session sent a message', // subagent / cross-session hand-back
+  '<agent-message',
+  'This session is being continued from a previous conversation', // compaction resume
+  'Stop hook feedback:',
+  '\\[SYSTEM NOTIFICATION',
+  'Your response above was cut off',
+  '\\(Re-invocation of /',
+  '\\[\\d+ prior /loop wakeup',
 ].join('|') + ')');
 
 const textOf = (msg) => {
@@ -261,7 +269,7 @@ if (problems.length) {
   console.error('INCONSISTENT REPORT, refusing to write:\n  ' + problems.join('\n  '));
   process.exit(3);
 }
-report.echoFilterVersion = 2;
+report.echoFilterVersion = 3;
 
 fs.writeFileSync(OUT, JSON.stringify(report, null, 1));
 fs.writeFileSync(OUT.replace(/\.json$/, '') + '-turns.json', JSON.stringify(S.humanTurns, null, 1));

package/adapters/grok/olko-github-pr/skills/codexloop/SKILL.md

@@ -8,7 +8,7 @@ description: >
   review", "fix codex comments", "codex loop", or wants to iterate on Codex PR review feedback.
 compatibility: GitHub only (Codex code review is a GitHub app). Requires git + gh (GitHub CLI) authenticated, and the Codex / ChatGPT connector app installed on the repo with code review enabled.
 metadata:
-  version: "1.0"
+  version: "1.1"
 allowed-tools: Bash(gh:*) Bash(git:*)
 ---
 <!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
@@ -70,6 +70,12 @@ Switch to the PR branch if not already on it. Capture `OWNER`/`REPO` (`gh repo v
 
 ## 2. The loop (max 5 iterations)
 
+At the end of every invocation, post exactly one top-level PR conversation comment summarizing
+the result, including iterations, comments fixed, comments rebutted, and anything remaining. This
+is required even when the loop times out or reaches its iteration cap; report that state honestly.
+End the comment with: **Useful? React with 👍 / 👎.** Do not post a separate summary comment for
+each iteration.
+
 Keep an explicit iteration counter and stop at 5: the cap is a real bound to enforce, not a
 figure of speech. Each pass through A–G is one iteration; on hitting the cap, go straight to the
 report and list what is still unresolved rather than starting a sixth.
@@ -191,6 +197,10 @@ gh pr view <PR> --json headRefOid -q .headRefOid   # must match
 
 If they differ, stop: the fix is not on the PR, so nothing may be resolved yet.
 
+Every fixed Codex thread must be replied to and resolved after this push is verified. A fix is not
+complete while its thread remains unresolved. If no code changed, rebutted threads can be replied
+to and resolved without a push.
+
 ### F. Reply to and resolve every addressed thread
 
 Only now, with the fixes pushed, reply and resolve. Fetch unresolved threads, **following
@@ -227,7 +237,10 @@ gh api graphql -f query='mutation { resolveReviewThread(input: {threadId: "THREA
 ```
 
 Resolve a thread only for comments authored by `$BOT` that you have fixed or rebutted: never
-blanket-resolve, and never resolve a human reviewer's thread.
+blanket-resolve, and never resolve a human reviewer's thread. For each fixed comment, verify the
+push first, reply with the change made, then resolve the thread and verify `isResolved: true`.
+For each rebutted comment, reply with the evidence and verify resolution. Do not report a comment
+as fixed or rebutted until its thread is confirmed resolved.
 
 Threads you are **rebutting** need no push, so they may be replied to and resolved regardless of
 whether step D changed code.

package/adapters/grok/olko-reflection/skills/agent-ops-retro/scripts/mine-transcripts.mjs

@@ -45,7 +45,6 @@ function walk(dir, out = []) {
   return out;
 }
 
-// A user-role text record that is really harness output, not something a person typed.
 // A user-role text record that is really harness output, not something a person typed.
 // Each alternative below was found by a run that mis-counted. The first pass caught the
 // obvious wrappers and still let 26% through: skill body dumps, image attachments,
@@ -62,6 +61,15 @@ const HARNESS = new RegExp('^(' + [
   '\\[Image #\\d+\\]',                    // bare attachment
   '\\[Image: source:',
   '\\[Pasted text',
+  // v3: the 2026-09-29 run found v2 still let 66% through, almost all of it these five.
+  'Another Claude session sent a message', // subagent / cross-session hand-back
+  '<agent-message',
+  'This session is being continued from a previous conversation', // compaction resume
+  'Stop hook feedback:',
+  '\\[SYSTEM NOTIFICATION',
+  'Your response above was cut off',
+  '\\(Re-invocation of /',
+  '\\[\\d+ prior /loop wakeup',
 ].join('|') + ')');
 
 const textOf = (msg) => {
@@ -261,7 +269,7 @@ if (problems.length) {
   console.error('INCONSISTENT REPORT, refusing to write:\n  ' + problems.join('\n  '));
   process.exit(3);
 }
-report.echoFilterVersion = 2;
+report.echoFilterVersion = 3;
 
 fs.writeFileSync(OUT, JSON.stringify(report, null, 1));
 fs.writeFileSync(OUT.replace(/\.json$/, '') + '-turns.json', JSON.stringify(S.humanTurns, null, 1));

package/catalog/skills.json

@@ -144,7 +144,7 @@
         },
         {
           "name": "codexloop",
-          "lookupName": "olko:codexloop",
+          "lookupName": "codexloop",
           "path": "plugins/olko-github-pr/skills/codexloop",
           "description": "Iteratively drives a GitHub PR to zero unresolved OpenAI Codex review comments, verifying every finding against the real code first, fixes only the correct ones, and rebuts false positives without changing correct code.",
           "tags": [

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@olegkoval/agent-skills",
-  "version": "1.49.1",
+  "version": "1.50.0",
   "private": false,
   "publishConfig": {
     "access": "public"

package/plugins/olko-apple-kit/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "olko-apple-kit",
   "description": "Build and ship Apple platform apps: macOS menubar apps, App Store submissions.",
-  "version": "1.49.1",
+  "version": "1.50.0",
   "author": {
     "name": "Oleg Koval"
   },

package/plugins/olko-creative/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "olko-creative",
   "description": "Creative and personal projects: photo galleries, music players, listings, wiki editing.",
-  "version": "1.49.1",
+  "version": "1.50.0",
   "author": {
     "name": "Oleg Koval"
   },

package/plugins/olko-garmin-kit/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "olko-garmin-kit",
   "description": "Build, test and publish Garmin Connect IQ watch faces.",
-  "version": "1.49.1",
+  "version": "1.50.0",
   "author": {
     "name": "Oleg Koval"
   },

package/plugins/olko-git-tools/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "olko-git-tools",
   "description": "Everyday git and GitHub CLI operations: conventional commits, branch hygiene.",
-  "version": "1.49.1",
+  "version": "1.50.0",
   "author": {
     "name": "Oleg Koval"
   },

package/plugins/olko-github-pr/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "olko-github-pr",
   "description": "Drive GitHub pull requests to merge-ready: review-bot loops, CI fixes, descriptions, dependency triage.",
-  "version": "1.49.1",
+  "version": "1.50.0",
   "author": {
     "name": "Oleg Koval"
   },

package/plugins/olko-github-pr/skills/codexloop/SKILL.md

@@ -8,7 +8,7 @@ description: >
   review", "fix codex comments", "codex loop", or wants to iterate on Codex PR review feedback.
 compatibility: GitHub only (Codex code review is a GitHub app). Requires git + gh (GitHub CLI) authenticated, and the Codex / ChatGPT connector app installed on the repo with code review enabled.
 metadata:
-  version: "1.0"
+  version: "1.1"
 allowed-tools: Bash(gh:*) Bash(git:*)
 ---
 
@@ -69,6 +69,12 @@ Switch to the PR branch if not already on it. Capture `OWNER`/`REPO` (`gh repo v
 
 ## 2. The loop (max 5 iterations)
 
+At the end of every invocation, post exactly one top-level PR conversation comment summarizing
+the result, including iterations, comments fixed, comments rebutted, and anything remaining. This
+is required even when the loop times out or reaches its iteration cap; report that state honestly.
+End the comment with: **Useful? React with 👍 / 👎.** Do not post a separate summary comment for
+each iteration.
+
 Keep an explicit iteration counter and stop at 5: the cap is a real bound to enforce, not a
 figure of speech. Each pass through A–G is one iteration; on hitting the cap, go straight to the
 report and list what is still unresolved rather than starting a sixth.
@@ -190,6 +196,10 @@ gh pr view <PR> --json headRefOid -q .headRefOid   # must match
 
 If they differ, stop: the fix is not on the PR, so nothing may be resolved yet.
 
+Every fixed Codex thread must be replied to and resolved after this push is verified. A fix is not
+complete while its thread remains unresolved. If no code changed, rebutted threads can be replied
+to and resolved without a push.
+
 ### F. Reply to and resolve every addressed thread
 
 Only now, with the fixes pushed, reply and resolve. Fetch unresolved threads, **following
@@ -226,7 +236,10 @@ gh api graphql -f query='mutation { resolveReviewThread(input: {threadId: "THREA
 ```
 
 Resolve a thread only for comments authored by `$BOT` that you have fixed or rebutted: never
-blanket-resolve, and never resolve a human reviewer's thread.
+blanket-resolve, and never resolve a human reviewer's thread. For each fixed comment, verify the
+push first, reply with the change made, then resolve the thread and verify `isResolved: true`.
+For each rebutted comment, reply with the evidence and verify resolution. Do not report a comment
+as fixed or rebutted until its thread is confirmed resolved.
 
 Threads you are **rebutting** need no push, so they may be replied to and resolved regardless of
 whether step D changed code.

package/plugins/olko-github-pr/skills/lekker-review/SKILL.md

@@ -86,6 +86,31 @@ No nitpicking. Critical and Important findings are reserved for things that
 could cause bugs, outages, data loss, security incidents, or real performance
 problems at scale.
 
+**Boundary-first review rule:** for stateful or integration-heavy changes,
+review the complete behavioral chain rather than the changed helper alone:
+
+```text
+production entry point
+→ decision point
+→ runtime realization
+→ downstream consumer
+→ persistence/cache/cleanup owner
+```
+
+Require the review to distinguish logical identity from physical/runtime
+identity, and to test the relevant transition matrix: success, `null`, `undefined`,
+exception, retry, fallback, rotation, cache reuse/eviction, proxy parity, and
+quoted/history input where applicable. A copied helper test is isolated
+evidence, not proof that the production boundary works.
+
+Every verdict-affecting finding should carry a boundary map and an evidence
+class. The report must distinguish source inspection, isolated tests,
+repository tests, composed production-entry probes, production probes, and
+hosted CI. Never upgrade one evidence class into another in the wording.
+
+After a fix, re-run the original proof *and* audit the newly changed lifecycle
+boundary for regressions. A green reproduction is necessary, not sufficient.
+
 **HARD RULE: the `## 💰 Review Cost` block is mandatory.** Every review MUST
 end with an evidence-backed cost block and no `<N>` placeholders. Use real
 numbers for measurements the host exposes; follow `references/output-format.md`
@@ -289,7 +314,7 @@ page for this PR.
 | Review agents               | 2 triage (haiku)      | 5 specialists (sonnet) | 5 specialists (sonnet)  |
 | Per-finding verification    | Criticals + Importants | Criticals + Importants | Criticals + Importants |
 | Completeness critic         | skip                  | skip                | included                   |
-| Proof-of-bug (failing test per Critical) | skip     | included (max 5)    | included (max 5)           |
+| Proof-of-bug (failing test per Critical or composed-boundary Important) | skip     | included (max 5)    | included (max 5)           |
 | Living review artifact      | included              | included            | included                   |
 | Housekeeping (optional memory/notes writeback) | skip | included            | included                   |
 | `--post`                    | supported             | supported           | supported                  |

package/plugins/olko-github-pr/skills/lekker-review/references/agents/completeness-critic.md

@@ -14,6 +14,18 @@ were declared "no findings" too quickly. For each angle:
 Be concrete: cite diff lines, not vibes. If you genuinely cannot find a missed
 angle, return "No gaps found."
 
+Always consider these maintainer-grade gaps before returning no gaps:
+- the real production entry point and downstream consumer were not exercised;
+- the selected value was not traced through runtime realization, persistence,
+  cleanup, cache reuse, or fallback;
+- logical identity was conflated with physical/runtime identity;
+- a state-transition matrix is missing for `None`, exceptions, retries,
+  rotation, proxying, or alternate transport;
+- the fix was checked only against the original symptom, not for a new defect
+  introduced at the changed ordering or lifecycle boundary;
+- the evidence is an isolated harness or local test but the review claims
+  composed behavior or hosted-CI acceptance.
+
 Agent findings:
 <AGENT_FINDINGS_SUMMARY>
 

package/plugins/olko-github-pr/skills/lekker-review/references/agents/implementation.md

@@ -37,7 +37,32 @@ Axes to cover:
   sort/dedup on large arrays that could be done at DB level.
 - Integration Contracts: Shopify API misuse, BC API assumptions, webhook
   idempotency, external API pagination not handled.
-- GraphQL pagination (GQL-1): for every GraphQL query in the diff that uses a
+
+Boundary contract and lifecycle map (required for every Critical/Important
+finding involving routing, persistence, caching, fallback, proxying, or an
+external integration):
+- `entryPoint`: identify the real production trigger that reaches the changed
+  code (HTTP route, webhook, CLI command, queue consumer, gateway ingress, etc.).
+- `decisionPoint`: identify where the behavior is selected or transformed.
+- `realizationPoint`: identify where the selected behavior becomes runtime state.
+- `consumer`: identify the downstream consumer that actually relies on the
+  contract, not merely the helper that constructs it.
+- `stateOwner`: identify the durable/session/cache owner when state crosses a
+  turn, request, retry, or process boundary.
+- `identityDimensions`: list every identity that must remain distinct, such as
+  logical session key, physical session id, provider alias, resolved provider,
+  model, and API mode.
+- `transitions`: list the relevant success, `null`, `undefined`, exception, retry, fallback,
+  session-rotation, cache-reuse, and proxy/alternate-transport transitions.
+- `evidenceClass`: label the strongest evidence actually checked: `source`,
+  `isolated-test`, `repository-test`, `composed-test`, `production-probe`, or
+  `hosted-ci`. Never call an isolated harness a production-path proof.
+
+Do not report a stateful/integration finding without this boundary object. If
+the production entry point or downstream consumer cannot be identified, mark
+the claim as unverified rather than inferring behavior from a helper alone.
+
+GraphQL pagination (GQL-1): for every GraphQL query in the diff that uses a
   nodes connection (`nodes { ... }`):
   (a) Check that `pageInfo { hasNextPage endCursor }` is present alongside nodes: if missing, Critical.
   (b) Check that all pages are fetched (a loop or recursion using endCursor): a single-page fetch is a bug, Critical.

package/plugins/olko-github-pr/skills/lekker-review/references/agents/prover.md

@@ -4,11 +4,18 @@
 
 ## Mission
 
-A Critical finding is an argument until someone runs it. Your job is to turn it
+A Critical finding, or an Important finding with a composed boundary map, is an
+argument until someone runs it. Your job is to turn it
 into a demonstration: write ONE test that asserts the CORRECT behavior of the
 code the finding targets, run it in the real worktree, and capture it failing
 for the exact reason the finding claims.
 
+For a finding with `boundary`, prefer entering through the recorded production
+entry point and reaching the recorded downstream consumer. Do not replace a
+composed proof with a copied helper test just because the helper is easier to
+import. If full composition is impossible, report the strongest lower evidence
+class honestly.
+
 Write the test as if the bug were already fixed. It must fail today precisely
 *because* it isn't fixed. **Never write a test that asserts the buggy behavior
 just to have something red** -- a proof that asserts wrongness is worthless and

package/plugins/olko-github-pr/skills/lekker-review/references/agents/test-quality.md

@@ -128,8 +128,26 @@ g) Mock smell: test the behavior, not the way it's built
    (time, randomness, injected network failure), or a dependency that genuinely
    cannot run in the test environment. The tell for a good mock: the behavior
    under test only exists because the boundary did something (e.g. a retry
-   banner that appears only when the fetch rejects). Even then, prefer an
-   injected simple fake over a module-level spy, and assert what the user sees.
+ banner that appears only when the fetch rejects). Even then, prefer an
+ injected simple fake over a module-level spy, and assert what the user sees.
+
+ h) Composed boundary and transition coverage
+ For every stateful or integration-heavy change, do not stop at testing the
+ helper. Trace the real entry point through the decision point, runtime
+ realization, downstream consumer, and persistence/cleanup owner. Require a
+ test or explicit evidence for the relevant transition matrix:
+ - success, `None`, exception, and disabled-feature paths;
+ - retry and fallback behavior;
+ - session/request rotation and cache reuse or eviction;
+ - proxy or alternate transport parity;
+ - quoted/history input versus newly authored input;
+ - provider/model/API-mode identity when routing is involved.
+
+ A test that only asserts a helper return value is `isolated-test` evidence,
+ not `composed-test` evidence. Flag a Critical/Important finding when the
+ changed contract is consumed through a different path than the test covers,
+ or when the test can pass while the stateful consumer still receives the
+ wrong identity or ordering.
 
 Report each per-line issue as:
   `test-file:line, <concise description of the gap or weakness>`

package/plugins/olko-github-pr/skills/lekker-review/references/agents/verifier.md

@@ -123,6 +123,31 @@ convention finding with no verifiable precedent does not ship.
 
 ---
 
+## Step 4b -- Boundary contract and evidence check
+
+For any Critical/Important finding involving routing, persistence, caching,
+fallback, proxying, quoted input, or an external integration, read the
+finding's `boundary` object. It should identify the real production entry
+point, decision point, runtime realization point, downstream consumer, state
+owner, and relevant identity dimensions/transitions.
+
+Reconstruct the path in `WORKTREE_PATH` from entry point to consumer. A copied
+helper test or a mock that never reaches the consumer is only isolated
+evidence. Do not confirm a verdict-affecting finding as production-path proof
+unless the claimed failure reaches the stateful consumer or the review clearly
+labels the evidence as isolated.
+
+If the finding has no boundary object or no usable production entry point or
+consumer, keep it unverified and non-blocking; drop it when the missing boundary
+is the crux of the claim. The workflow enforces this as an unverified observation
+even if a verifier confirms it. Record the strongest evidence class actually checked
+(`source`, `isolated-test`, `repository-test`, `composed-test`,
+`production-probe`, or `hosted-ci`) in the reasoning.
+
+Build a small transition matrix for the affected contract. At minimum check
+success, `null`, `undefined`, exception, retry/fallback, state rotation, cache reuse or
+eviction, and proxy/alternate transport whenever those transitions exist.
+
 ## Step 5 -- Fix validation
 
 Before confirming the finding, identify the callers and consumers of the changed

package/plugins/olko-github-pr/skills/lekker-review/references/fix-mode.md

@@ -210,6 +210,29 @@ check after any revert triggered here before moving on.
 
 ---
 
+## Step 5c -- Fix delta audit
+
+After the original proof flips red → green, audit the *new* boundary created by
+the fix. Do not assume that making the original assertion pass makes the
+lifecycle safe.
+
+For each fixed Critical/Important finding involving state, routing, ordering,
+proxying, persistence, caching, fallback, or quoted input:
+
+1. Re-read the entire changed path from the production entry point to the
+   downstream consumer.
+2. Re-run the relevant transition matrix: success, `None`, exception, retry,
+   fallback, rotation, cache reuse/eviction, and alternate transport where
+   applicable.
+3. Check that logical identity, runtime identity, provider/API identity, and
+   durable identity are still distinct where the contract requires it.
+4. Add a focused regression probe when the fix moved work across an ordering or
+   lifecycle boundary. The probe must enter through the real path when feasible.
+
+If the audit finds a new failure, revert the whole group and mark it
+`failed: fix-delta-regression`. A green original proof is not sufficient to
+commit a fix that breaks a neighboring transition.
+
 ## Step 6 -- Commit (local only)
 
 One commit per file group, in group order. Stage explicitly -- never `git add -A`,

package/plugins/olko-github-pr/skills/lekker-review/workflow.js

@@ -8,11 +8,30 @@ export const meta = {
 // Schemas
 // ---------------------------------------------------------------------------
 
+const BOUNDARY_SCHEMA = {
+  type: 'object',
+  required: ['entryPoint', 'consumer'],
+  properties: {
+    entryPoint:         { type: 'string', minLength: 1, pattern: '\\S' },
+    decisionPoint:       { type: 'string' },
+    realizationPoint:   { type: 'string' },
+    consumer:           { type: 'string', minLength: 1, pattern: '\\S' },
+    stateOwner:         { type: 'string' },
+    evidenceClass:      { type: 'string' },
+    identityDimensions: { type: 'array', items: { type: 'string' } },
+    transitions:        { type: 'array', items: { type: 'string' } },
+  },
+}
+
 const FINDINGS_ARRAY_SCHEMA = {
   type: 'array',
   items: {
     type: 'object',
     required: ['file', 'line', 'severity', 'title', 'description', 'badCode', 'fix'],
+    anyOf: [
+      { properties: { severity: { enum: ['observation', 'idiomatic'] } } },
+      { required: ['boundary'] },
+    ],
     properties: {
       file:        { type: 'string' },
       line:        { type: 'integer' },
@@ -23,6 +42,7 @@ const FINDINGS_ARRAY_SCHEMA = {
       fix:         { type: 'string' },
       precedent:   { type: 'string' },
       rule:        { type: 'string', minLength: 1, pattern: '\\S' },
+      boundary:    BOUNDARY_SCHEMA,
     },
   },
 }
@@ -267,6 +287,41 @@ function shouldVerify(finding) {
   return finding.severity === 'critical' || finding.severity === 'important'
 }
 
+/**
+ * Does the finding carry enough of a composed boundary map to attempt a
+ * proof? Requires an entry point and a consumer, plus at least one of a
+ * realization point, state owner, or recorded transition.
+ */
+function hasBoundaryProofSurface(finding) {
+  const boundary = finding && finding.boundary
+  if (!boundary || typeof boundary !== 'object') {
+    return false
+  }
+  const hasText = function(value) {
+    return typeof value === 'string' && value.trim().length > 0
+  }
+  const hasList = function(value) {
+    return Array.isArray(value) && value.length > 0
+  }
+  return hasText(boundary.entryPoint)
+    && hasText(boundary.consumer)
+    && (
+      hasText(boundary.realizationPoint)
+      || hasText(boundary.stateOwner)
+      || hasList(boundary.transitions)
+    )
+}
+
+/**
+ * Does this finding qualify for the Prove stage? Every Critical finding
+ * qualifies; an Important finding only qualifies when it has a composed
+ * boundary map to prove against.
+ */
+function shouldProve(finding) {
+  return finding.severity === 'critical'
+    || (finding.severity === 'important' && hasBoundaryProofSurface(finding))
+}
+
 function normalizeProof(result) {
   const hasText = function(value) {
     return typeof value === 'string' && value.trim().length > 0
@@ -520,7 +575,29 @@ const budgetAtStart = budget.spent()
   // rule-specific checks and skip only its runtime-oriented challenges.
   // -------------------------------------------------------------------------
 
+  // A model verdict cannot replace the required production boundary map.
+  function enforceBoundary(finding) {
+    if (!shouldVerify(finding)) return finding
+    const boundary = finding.boundary
+    const hasText = function(value) {
+      return typeof value === 'string' && value.trim().length > 0
+    }
+    if (boundary && typeof boundary === 'object' && !Array.isArray(boundary)
+        && hasText(boundary.entryPoint) && hasText(boundary.consumer)) {
+      return finding
+    }
+    downgradedCount++
+    const unverified = Object.assign({}, finding, {
+      severity: 'observation',
+      verificationStatus: 'unverified',
+      verifierReasoning: 'Missing boundary object or identified production entry point/downstream consumer; downgraded to non-blocking',
+    })
+    delete unverified.proof
+    return unverified
+  }
+
   async function verifyAll(findings) {
+    findings = findings.map(enforceBoundary)
     const inScope = findings.filter(function(f) {
       return shouldVerify(f)
     })
@@ -704,7 +781,8 @@ const budgetAtStart = budget.spent()
           }
 
           // Verify the new finding through the same verifier path
-          const newFinding = Object.assign({}, reResult.findings[0])
+          const newFinding = enforceBoundary(Object.assign({}, reResult.findings[0]))
+          if (newFinding.verificationStatus === 'unverified') return [newFinding]
           newFinding._dimension = `critic:${angle.axis}`
 
           agentCount++
@@ -749,9 +827,13 @@ const budgetAtStart = budget.spent()
 
   } // end ENGINE === 'workflow' branch
 
+  // Recheck after critic dedup and imported results, before proof promotion.
+  finalFindings = finalFindings.map(enforceBoundary)
+
   // -------------------------------------------------------------------------
-  // Prove: for each Critical finding (excluding hard rules, which are policy
-  // violations with no runtime failure to demonstrate), attempt to produce an
+  // Prove: for each Critical finding and each Important finding with a
+  // composed boundary map (excluding hard rules, which are policy violations
+  // with no runtime failure to demonstrate), attempt to produce an
   // executable failing test in the worktree. Only runs with a worktree and
   // outside scan depth, and is capped so a pathological finding count can't
   // blow the budget.
@@ -770,7 +852,7 @@ const budgetAtStart = budget.spent()
 
   if (worktreePath && depth !== 'scan') {
     const proveCandidates = finalFindings.filter(function(f) {
-      return f.severity === 'critical' && !isHardRule(f)
+      return shouldProve(f) && !isHardRule(f)
     })
 
     if (proveCandidates.length > 0) {
@@ -779,7 +861,7 @@ const budgetAtStart = budget.spent()
       const capped = proveCandidates.slice(0, 5)
       const skipped = proveCandidates.length - capped.length
       if (skipped > 0) {
-        log(`Prove: capping at 5 provers, skipping ${skipped} additional critical finding(s)`)
+        log(`Prove: capping at 5 provers, skipping ${skipped} additional finding(s)`)
       }
 
       await batched(capped.map(function(finding) {

package/plugins/olko-obsidian/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "olko-obsidian",
   "description": "Keep an Obsidian vault in sync with work: PR sync, task rollover, morning routine.",
-  "version": "1.49.1",
+  "version": "1.50.0",
   "author": {
     "name": "Oleg Koval"
   },

package/plugins/olko-product/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "olko-product",
   "description": "Take a product idea to a shippable build: MVP passes, full-stack scaffolds, UX/UI quality loops, launch plans.",
-  "version": "1.49.1",
+  "version": "1.50.0",
   "author": {
     "name": "Oleg Koval"
   },

package/plugins/olko-reflection/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "olko-reflection",
   "description": "Look back and improve: self-critique, retrospectives, performance review, rapid learning.",
-  "version": "1.49.1",
+  "version": "1.50.0",
   "author": {
     "name": "Oleg Koval"
   },

package/plugins/olko-reflection/skills/agent-ops-retro/scripts/mine-transcripts.mjs

@@ -45,7 +45,6 @@ function walk(dir, out = []) {
   return out;
 }
 
-// A user-role text record that is really harness output, not something a person typed.
 // A user-role text record that is really harness output, not something a person typed.
 // Each alternative below was found by a run that mis-counted. The first pass caught the
 // obvious wrappers and still let 26% through: skill body dumps, image attachments,
@@ -62,6 +61,15 @@ const HARNESS = new RegExp('^(' + [
   '\\[Image #\\d+\\]',                    // bare attachment
   '\\[Image: source:',
   '\\[Pasted text',
+  // v3: the 2026-09-29 run found v2 still let 66% through, almost all of it these five.
+  'Another Claude session sent a message', // subagent / cross-session hand-back
+  '<agent-message',
+  'This session is being continued from a previous conversation', // compaction resume
+  'Stop hook feedback:',
+  '\\[SYSTEM NOTIFICATION',
+  'Your response above was cut off',
+  '\\(Re-invocation of /',
+  '\\[\\d+ prior /loop wakeup',
 ].join('|') + ')');
 
 const textOf = (msg) => {
@@ -261,7 +269,7 @@ if (problems.length) {
   console.error('INCONSISTENT REPORT, refusing to write:\n  ' + problems.join('\n  '));
   process.exit(3);
 }
-report.echoFilterVersion = 2;
+report.echoFilterVersion = 3;
 
 fs.writeFileSync(OUT, JSON.stringify(report, null, 1));
 fs.writeFileSync(OUT.replace(/\.json$/, '') + '-turns.json', JSON.stringify(S.humanTurns, null, 1));

package/plugins/olko-release/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "olko-release",
   "description": "Ship a release: semantic-release setup, changelogs, store listing copy, release-day routine.",
-  "version": "1.49.1",
+  "version": "1.50.0",
   "author": {
     "name": "Oleg Koval"
   },

package/plugins/olko-skill-meta/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "olko-skill-meta",
   "description": "Author and maintain agent skills and the AI toolchain itself.",
-  "version": "1.49.1",
+  "version": "1.50.0",
   "author": {
     "name": "Oleg Koval"
   },

package/plugins/olko-web-ops/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "olko-web-ops",
   "description": "Operate a website: WAF rules, search console audits, analytics bootstrap, docs indexes.",
-  "version": "1.49.1",
+  "version": "1.50.0",
   "author": {
     "name": "Oleg Koval"
   },