LightbridgeLab · sebastientaggart · Apr 8, 2026 · Apr 8, 2026 · Apr 8, 2026 · Apr 8, 2026
diff --git a/.agents/skills/deploy/SKILL.md b/.agents/skills/deploy/SKILL.md
@@ -1,6 +1,6 @@
 ---
 name: deploy
-description: Bump the project version, create a GitHub Release, and promote to production — handles both versioning and releasing in one step
+description: Code Cannon: Bump the project version, create a GitHub Release, and promote to production — handles both versioning and releasing in one step
 ---
 
 > **Codex CLI:** This skill is triggered by description matching. State any arguments in your message. Sub-agent spawning is not supported — perform any review steps inline.
@@ -235,4 +235,4 @@ After the command runs, note the release URL from the output.
 Tell the user:
 
 > "Released vX.Y.Z. Issues #N, #M closed automatically. GitHub Release vX.Y.Z created at `<url>`. Run `make deploy-prod` to ship to production."
-<!-- generated by CodeCannon/sync.sh | skill: deploy | adapter: codex | hash: 31067fad | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
+<!-- generated by CodeCannon/sync.sh | skill: deploy | adapter: codex | hash: 216e7949 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
diff --git a/.agents/skills/qa/SKILL.md b/.agents/skills/qa/SKILL.md
@@ -1,6 +1,6 @@
 ---
 name: qa
-description: View the QA queue or review a specific issue
+description: Code Cannon: View the QA queue or review a specific issue
 ---
 
 > **Codex CLI:** This skill is triggered by description matching. State any arguments in your message. Sub-agent spawning is not supported — perform any review steps inline.
@@ -141,4 +141,4 @@ After applying labels, tell the user what was done:
 - Never post the comment without showing it to the user first.
 - Never apply labels without user confirmation (the confirmation in Step 3 is the single gate for both posting the comment and applying labels).
 - Never merge, deploy, or take any action beyond labeling and commenting.
-<!-- generated by CodeCannon/sync.sh | skill: qa | adapter: codex | hash: dc360e69 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
+<!-- generated by CodeCannon/sync.sh | skill: qa | adapter: codex | hash: 1aa8055b | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
diff --git a/.agents/skills/review/SKILL.md b/.agents/skills/review/SKILL.md
@@ -1,6 +1,6 @@
 ---
 name: review
-description: Run a standalone code review on a pull request
+description: Code Cannon: Run a standalone code review on a pull request
 ---
 
 > **Codex CLI:** This skill is triggered by description matching. State any arguments in your message. Sub-agent spawning is not supported — perform any review steps inline.
@@ -65,4 +65,4 @@ After the review agent completes, relay its verdict to the user:
 - This command does not commit, push, or merge anything. It only reviews.
 - It may be called manually at any time, not just from `/submit-for-review`.
 - The review comment is posted to GitHub for the audit trail.
-<!-- generated by CodeCannon/sync.sh | skill: review | adapter: codex | hash: e781dae2 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
+<!-- generated by CodeCannon/sync.sh | skill: review | adapter: codex | hash: 4eb6967b | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
diff --git a/.agents/skills/setup/SKILL.md b/.agents/skills/setup/SKILL.md
@@ -1,6 +1,6 @@
 ---
 name: setup
-description: Detect setup state, guide first-time configuration, populate labels, and walk through optional config values
+description: Code Cannon: Detect setup state, guide first-time configuration, populate labels, and walk through optional config values
 ---
 
 > **Codex CLI:** This skill is triggered by description matching. State any arguments in your message. Sub-agent spawning is not supported — perform any review steps inline.
@@ -475,4 +475,4 @@ Add a note: `/start` can be used to create well-formed GitHub issues without wri
 - Never fetch more than 100 labels in a single command. `gh label list --limit 100` is the ceiling.
 - Do not skip any human gate in Phase 2 or Phase 3 — each write requires confirmation.
 - If the user skips a config value, do not ask again. Move on.
-<!-- generated by CodeCannon/sync.sh | skill: setup | adapter: codex | hash: fa142ad2 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
+<!-- generated by CodeCannon/sync.sh | skill: setup | adapter: codex | hash: daa5f140 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
diff --git a/.agents/skills/start/SKILL.md b/.agents/skills/start/SKILL.md
@@ -1,6 +1,6 @@
 ---
 name: start
-description: Start a new feature or bugfix
+description: Code Cannon: Start a new feature or bugfix
 ---
 
 > **Codex CLI:** This skill is triggered by description matching. State any arguments in your message. Sub-agent spawning is not supported — perform any review steps inline.
@@ -230,4 +230,4 @@ When done, say: **"The code is ready for review. Please run `make dev` and test
 - The issue is assigned to `@me` at creation. If you are creating a ticket on someone else's behalf, remove the assignee after creation with `gh issue edit <number> --remove-assignee @me`.
 - Apply resolved labels and milestone to every new issue. Label resolution order: per-invocation flag → pool selection from `bug, documentation, enhancement, chore` → omit (or create if `false` is `true`). Never apply a label not in `bug, documentation, enhancement, chore` unless `false` is `true`.
 - Milestone resolution order: per-invocation flag → auto-detected from GitHub open milestones. Never prompt for a milestone more than once per invocation.
-<!-- generated by CodeCannon/sync.sh | skill: start | adapter: codex | hash: 8c5a4402 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
+<!-- generated by CodeCannon/sync.sh | skill: start | adapter: codex | hash: 97886867 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
diff --git a/.agents/skills/status/SKILL.md b/.agents/skills/status/SKILL.md
@@ -1,6 +1,6 @@
 ---
 name: status
-description: Summarize in-progress and recently completed work from GitHub and git
+description: Code Cannon: Summarize in-progress and recently completed work from GitHub and git
 ---
 
 > **Codex CLI:** This skill is triggered by description matching. State any arguments in your message. Sub-agent spawning is not supported — perform any review steps inline.
@@ -241,4 +241,4 @@ Do not post, comment, write files, or take any action. Output only.
 - If `gh` is unauthenticated or any fetch fails, report the error and stop immediately.
 - Do not retry failed commands.
 - Strip the leading `@` from the subject when passing to `gh` flags that do not accept it.
-<!-- generated by CodeCannon/sync.sh | skill: status | adapter: codex | hash: 08068d91 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
+<!-- generated by CodeCannon/sync.sh | skill: status | adapter: codex | hash: b942c6b6 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
diff --git a/.agents/skills/submit-for-review/SKILL.md b/.agents/skills/submit-for-review/SKILL.md
@@ -1,6 +1,6 @@
 ---
 name: submit-for-review
-description: Type-check, commit, open PR, review, and merge to the integration branch
+description: Code Cannon: Type-check, commit, open PR, review, and merge to the integration branch
 ---
 
 > **Codex CLI:** This skill is triggered by description matching. State any arguments in your message. Sub-agent spawning is not supported — perform any review steps inline.
@@ -200,6 +200,56 @@ Report success based on mode:
 
 ---
 
+## Step 9 — Offer follow-up issues for non-blocking findings
+
+**Gate this step entirely** if any of the following are true:
+- `ai` is `"off"` (no review was performed).
+- The merge in Step 8 did not actually happen (e.g. `ai` mode with REQUEST CHANGES).
+- The review output contains no non-blocking findings.
+
+**Collect non-blocking findings** from the review output retained from Step 7:
+- Always include lines starting with `[WARNING]` or `[NOTE]`.
+- If `ai` is `"advisory"`, also include any `[CRITICAL]` lines — the user chose to merge over them, so they are now follow-up candidates too.
+- If `ai` is `"ai"`, do not include `[CRITICAL]` lines (there should not be any on the merge path, but guard anyway).
+
+If the collected list is empty, skip the rest of this step silently.
+
+**Present and ask once.** Show the findings as a numbered list (preserve the `[WARNING]` / `[NOTE]` / `[CRITICAL]` prefix in the display for clarity) and ask exactly:
+
+> "The review flagged N non-blocking finding(s). Create follow-up issues for any of them? Enter numbers (e.g. `1,3`), `all`, or `none`."
+
+Accept: comma-separated numbers, `all`, or `none`/`skip`/empty. If the input is unparseable, re-prompt once; if still invalid, treat as `none` and move on.
+
+**Create the selected issues.** For each selected finding, run `gh issue create` with explicit flags:
+
+```
+gh issue create \
+  --title "<finding text with [WARNING]/[NOTE]/[CRITICAL] prefix stripped, trimmed to a standalone sentence>" \
+  --body "$(cat <<'EOF'
+Follow-up from PR #<merged-pr-number> — auto-proposed from the code review.
+
+**Finding:** <full finding text, prefix included>
+
+See the review comment on the PR for context.
+EOF
+)" \
+  [--label "<pool-selected labels>"]
+```
+
+Label resolution for each follow-up issue: use the pool-based selection tier from `/start` — pick 1–3 labels from `bug, documentation, enhancement, chore` that genuinely fit the finding. If `bug, documentation, enhancement, chore` is empty or no pool label fits, omit `--label`. Do not attempt per-invocation flag resolution (there is no flag here) and do not create new labels regardless of `false`.
+
+Do **not** pass `--milestone` — follow-ups are future work and should not inherit the current sprint.
+
+Do **not** pass `--assignee @me` — these are backlog items, not immediately assigned.
+
+If a single `gh issue create` call fails, report the failure for that finding and continue with the remaining selections.
+
+**Report the result:**
+- If one or more issues were created: `"Created N follow-up issue(s): #X, #Y, #Z"`.
+- If the user chose `none` or all creations were skipped: say nothing further, proceed to end.
+
+---
+
 ## Important constraints
 
 - Never skip `make check`. A failed check is a hard stop.
@@ -208,4 +258,5 @@ Report success based on mode:
 - When `ai` is `"off"`, skip the review agent entirely — merge immediately after checks pass.
 - `/submit-for-review` merges only to `dev` — never directly to `main`.
 - If `make merge` fails for any reason, report it and stop — do not attempt workarounds.
-<!-- generated by CodeCannon/sync.sh | skill: submit-for-review | adapter: codex | hash: 1675613b | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
+- The follow-up issue offer in Step 9 runs only after a successful merge and only when the review produced non-blocking findings. Never prompt the user for follow-ups when the review blocked the merge — those findings should be fixed, not ticketed.
+<!-- generated by CodeCannon/sync.sh | skill: submit-for-review | adapter: codex | hash: a10214da | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
diff --git a/.claude/commands/deploy.md b/.claude/commands/deploy.md
@@ -1,4 +1,4 @@
-Bump the project version, create a GitHub Release, and promote to production — handles both versioning and releasing in one step
+Code Cannon: Bump the project version, create a GitHub Release, and promote to production — handles both versioning and releasing in one step
 
 ---
 
@@ -230,4 +230,4 @@ After the command runs, note the release URL from the output.
 Tell the user:
 
 > "Released vX.Y.Z. Issues #N, #M closed automatically. GitHub Release vX.Y.Z created at `<url>`. Run `make deploy-prod` to ship to production."
-<!-- generated by CodeCannon/sync.sh | skill: deploy | adapter: claude | hash: 4e4a48f5 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
+<!-- generated by CodeCannon/sync.sh | skill: deploy | adapter: claude | hash: e0dd0480 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
diff --git a/.claude/commands/qa.md b/.claude/commands/qa.md
@@ -1,4 +1,4 @@
-View the QA queue or review a specific issue
+Code Cannon: View the QA queue or review a specific issue
 
 ---
 
@@ -136,4 +136,4 @@ After applying labels, tell the user what was done:
 - Never post the comment without showing it to the user first.
 - Never apply labels without user confirmation (the confirmation in Step 3 is the single gate for both posting the comment and applying labels).
 - Never merge, deploy, or take any action beyond labeling and commenting.
-<!-- generated by CodeCannon/sync.sh | skill: qa | adapter: claude | hash: ac0a4a39 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
+<!-- generated by CodeCannon/sync.sh | skill: qa | adapter: claude | hash: 7779c669 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
diff --git a/.claude/commands/review.md b/.claude/commands/review.md
@@ -1,4 +1,4 @@
-Run a standalone code review on a pull request
+Code Cannon: Run a standalone code review on a pull request
 
 ---
 
@@ -60,4 +60,4 @@ After the review agent completes, relay its verdict to the user:
 - This command does not commit, push, or merge anything. It only reviews.
 - It may be called manually at any time, not just from `/submit-for-review`.
 - The review comment is posted to GitHub for the audit trail.
-<!-- generated by CodeCannon/sync.sh | skill: review | adapter: claude | hash: 3ae6766a | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
+<!-- generated by CodeCannon/sync.sh | skill: review | adapter: claude | hash: 87cdfdad | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
diff --git a/.claude/commands/setup.md b/.claude/commands/setup.md
@@ -1,4 +1,4 @@
-Detect setup state, guide first-time configuration, populate labels, and walk through optional config values
+Code Cannon: Detect setup state, guide first-time configuration, populate labels, and walk through optional config values
 
 ---
 
@@ -470,4 +470,4 @@ Add a note: `/start` can be used to create well-formed GitHub issues without wri
 - Never fetch more than 100 labels in a single command. `gh label list --limit 100` is the ceiling.
 - Do not skip any human gate in Phase 2 or Phase 3 — each write requires confirmation.
 - If the user skips a config value, do not ask again. Move on.
-<!-- generated by CodeCannon/sync.sh | skill: setup | adapter: claude | hash: 1704e176 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
+<!-- generated by CodeCannon/sync.sh | skill: setup | adapter: claude | hash: e2f06373 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
diff --git a/.claude/commands/start.md b/.claude/commands/start.md
@@ -1,4 +1,4 @@
-Start a new feature or bugfix
+Code Cannon: Start a new feature or bugfix
 
 ---
 
@@ -225,4 +225,4 @@ When done, say: **"The code is ready for review. Please run `make dev` and test
 - The issue is assigned to `@me` at creation. If you are creating a ticket on someone else's behalf, remove the assignee after creation with `gh issue edit <number> --remove-assignee @me`.
 - Apply resolved labels and milestone to every new issue. Label resolution order: per-invocation flag → pool selection from `bug, documentation, enhancement, chore` → omit (or create if `false` is `true`). Never apply a label not in `bug, documentation, enhancement, chore` unless `false` is `true`.
 - Milestone resolution order: per-invocation flag → auto-detected from GitHub open milestones. Never prompt for a milestone more than once per invocation.
-<!-- generated by CodeCannon/sync.sh | skill: start | adapter: claude | hash: 7dea2caf | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
+<!-- generated by CodeCannon/sync.sh | skill: start | adapter: claude | hash: 972bf405 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
diff --git a/.claude/commands/status.md b/.claude/commands/status.md
@@ -1,4 +1,4 @@
-Summarize in-progress and recently completed work from GitHub and git
+Code Cannon: Summarize in-progress and recently completed work from GitHub and git
 
 ---
 
@@ -236,4 +236,4 @@ Do not post, comment, write files, or take any action. Output only.
 - If `gh` is unauthenticated or any fetch fails, report the error and stop immediately.
 - Do not retry failed commands.
 - Strip the leading `@` from the subject when passing to `gh` flags that do not accept it.
-<!-- generated by CodeCannon/sync.sh | skill: status | adapter: claude | hash: 9e27a4dc | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
+<!-- generated by CodeCannon/sync.sh | skill: status | adapter: claude | hash: eb38c883 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
diff --git a/.claude/commands/submit-for-review.md b/.claude/commands/submit-for-review.md
@@ -1,4 +1,4 @@
-Type-check, commit, open PR, review, and merge to the integration branch
+Code Cannon: Type-check, commit, open PR, review, and merge to the integration branch
 
 ---
 
@@ -195,6 +195,56 @@ Report success based on mode:
 
 ---
 
+## Step 9 — Offer follow-up issues for non-blocking findings
+
+**Gate this step entirely** if any of the following are true:
+- `ai` is `"off"` (no review was performed).
+- The merge in Step 8 did not actually happen (e.g. `ai` mode with REQUEST CHANGES).
+- The review output contains no non-blocking findings.
+
+**Collect non-blocking findings** from the review output retained from Step 7:
+- Always include lines starting with `[WARNING]` or `[NOTE]`.
+- If `ai` is `"advisory"`, also include any `[CRITICAL]` lines — the user chose to merge over them, so they are now follow-up candidates too.
+- If `ai` is `"ai"`, do not include `[CRITICAL]` lines (there should not be any on the merge path, but guard anyway).
+
+If the collected list is empty, skip the rest of this step silently.
+
+**Present and ask once.** Show the findings as a numbered list (preserve the `[WARNING]` / `[NOTE]` / `[CRITICAL]` prefix in the display for clarity) and ask exactly:
+
+> "The review flagged N non-blocking finding(s). Create follow-up issues for any of them? Enter numbers (e.g. `1,3`), `all`, or `none`."
+
+Accept: comma-separated numbers, `all`, or `none`/`skip`/empty. If the input is unparseable, re-prompt once; if still invalid, treat as `none` and move on.
+
+**Create the selected issues.** For each selected finding, run `gh issue create` with explicit flags:
+
+```
+gh issue create \
+  --title "<finding text with [WARNING]/[NOTE]/[CRITICAL] prefix stripped, trimmed to a standalone sentence>" \
+  --body "$(cat <<'EOF'
+Follow-up from PR #<merged-pr-number> — auto-proposed from the code review.
+
+**Finding:** <full finding text, prefix included>
+
+See the review comment on the PR for context.
+EOF
+)" \
+  [--label "<pool-selected labels>"]
+```
+
+Label resolution for each follow-up issue: use the pool-based selection tier from `/start` — pick 1–3 labels from `bug, documentation, enhancement, chore` that genuinely fit the finding. If `bug, documentation, enhancement, chore` is empty or no pool label fits, omit `--label`. Do not attempt per-invocation flag resolution (there is no flag here) and do not create new labels regardless of `false`.
+
+Do **not** pass `--milestone` — follow-ups are future work and should not inherit the current sprint.
+
+Do **not** pass `--assignee @me` — these are backlog items, not immediately assigned.
+
+If a single `gh issue create` call fails, report the failure for that finding and continue with the remaining selections.
+
+**Report the result:**
+- If one or more issues were created: `"Created N follow-up issue(s): #X, #Y, #Z"`.
+- If the user chose `none` or all creations were skipped: say nothing further, proceed to end.
+
+---
+
 ## Important constraints
 
 - Never skip `make check`. A failed check is a hard stop.
@@ -203,4 +253,5 @@ Report success based on mode:
 - When `ai` is `"off"`, skip the review agent entirely — merge immediately after checks pass.
 - `/submit-for-review` merges only to `dev` — never directly to `main`.
 - If `make merge` fails for any reason, report it and stop — do not attempt workarounds.
-<!-- generated by CodeCannon/sync.sh | skill: submit-for-review | adapter: claude | hash: 90e3dd51 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->
+- The follow-up issue offer in Step 9 runs only after a successful merge and only when the review produced non-blocking findings. Never prompt the user for follow-ups when the review blocked the merge — those findings should be fixed, not ticketed.
+<!-- generated by CodeCannon/sync.sh | skill: submit-for-review | adapter: claude | hash: 29a2a831 | DO NOT EDIT — run CodeCannon/sync.sh to regenerate -->