@olegkoval/agent-skills 1.49.0 → 1.49.2

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

@@ -13,6 +13,10 @@ Agent-agnostic skill collection for Codex, Claude, Cursor, Grok, and other skill
 
 **Browse the catalog: [skills.olegkoval.com](https://skills.olegkoval.com)**
 
+**A separate project by Oleg:** [Factory](https://factory.olegkoval.com/) is an MIT-licensed
+skill for Claude Code and Codex that makes delivery claims answer to acceptance criteria and
+evidence. [Inspect one full documented run](https://factory.olegkoval.com/case-studies/development-hydration-warning/).
+
 These skills are opinionated by design. They encode working defaults, preferred tools, and repeatable workflows instead of trying to be neutral snippets. Treat them as starting points with taste: useful out of the box, easy to inspect, and specific enough for an agent to execute consistently.
 
 ```
@@ -111,7 +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-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": "1.49.0",
+  "version": "1.49.2",
   "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": "1.49.0",
+  "version": "1.49.2",
   "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": "1.49.0",
+  "version": "1.49.2",
   "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": "1.49.0",
+  "version": "1.49.2",
   "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": "1.49.0",
+  "version": "1.49.2",
   "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": "1.49.0",
+  "version": "1.49.2",
   "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-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": "1.49.0",
+  "version": "1.49.2",
   "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": "1.49.0",
+  "version": "1.49.2",
   "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": "1.49.0",
+  "version": "1.49.2",
   "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": "1.49.0",
+  "version": "1.49.2",
   "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": "1.49.0",
+  "version": "1.49.2",
   "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": "1.49.0",
+  "version": "1.49.2",
   "author": {
     "name": "Oleg Koval"
   },

package/site/build.mjs

@@ -19,6 +19,8 @@ const out = join(root, "_site");
 
 const SITE_URL = "https://skills.olegkoval.com";
 const PORTFOLIO = "https://www.olegkoval.com";
+const FACTORY_URL = "https://factory.olegkoval.com/";
+const FACTORY_CASE_STUDY_URL = `${FACTORY_URL}case-studies/development-hydration-warning/`;
 const REPO = "https://github.com/oleg-koval/agent-skills";
 const CNAME = "skills.olegkoval.com";
 const GA_MEASUREMENT_ID = "G-NV8Q2H8YV0";
@@ -287,6 +289,7 @@ ${installSection(packages[0].lookupName)}
     <p>Every workflow has one canonical skill package. Tool-specific adapters are generated from it, so the marketplace, source files, and this site stay aligned.</p>
   </div>
   <a class="quiet-link" href="${PORTFOLIO}" data-analytics-event="portfolio_visit" data-analytics-location="about">More open-source work and writing at olegkoval.com <span aria-hidden="true">↗</span></a>
+  <p>For proof-oriented coding-agent delivery, explore <a href="${FACTORY_URL}">Factory</a>, Oleg's separate MIT-licensed skill for Claude Code and Codex. <a href="${FACTORY_CASE_STUDY_URL}">Inspect a full documented run</a>.</p>
 </section>`;
 
   return layout({