Drop the Close Field, Match AGENTS.md's Own Unlabeled Shape

[ptr727]

Follow-up to #1074/#1079 (issue #1070), found by the develop -> main promotion PR (#1077)'s second review round.

Copilot flagged the Close: field #1079 introduced as a non-canonical key: AGENTS.md's own template ("Context and Delegation Discipline") has exactly 5 labeled fields (Task/Paths/Rules that bind this task/Return/Bounds) followed by one unlabeled trailing sentence, not a 6th labeled field. local-strict-review/SKILL.md's own "Running It" section says to follow that exact shape.

Round 1 fix (commit 2778010): dropped the Close: label, went back to an unlabeled trailing line in the same position AGENTS.md's own closing sentence occupies, kept #1079's "quote X into the prompt" phrasing. A fresh Copilot round then flagged that this still read as an imperative instruction addressed to the subagent, who cannot fulfil it (no AGENTS.md access) - the same ambiguity #1079 had already addressed once.

Round 2 fix (commit 2faa0e0, current): replaced the imperative sentence with an explicit angle-bracket placeholder, matching AGENTS.md's own template syntax exactly (which uses <...> for every field value). This is the second use of that convention in this file, not a new one - <target> already appears the same way at line 40. Fails safe if pasted unsubstituted: an obvious unfilled token rather than a misleading instruction.

Ran local-strict-review against this branch's diff before each push, explicitly asked to hunt for a reason a further round could still be needed. Round 2's review: no confirmed defect, and a specific, honest assessment of why this shape is unlikely to bounce again (matches an established in-file convention, fails safe, closes every prior round's concern simultaneously).

[qodo-code-review]

PR Summary by Qodo

Restore the canonical strict-review prompt shape

🐞 Bug fix📝 Documentation⚙️ Configuration changes🕐 Less than 10 minutes

AI Description

• Restore the strict-review brief’s five-field shape with an unlabeled closing instruction.
• Clarify the AGENTS.md closing rule becomes the brief’s final prompt line.
• Synchronize distributed skill copies and refresh the plugin source digest.

Diagram

graph TD
A["Canonical skill"] --> B["Claude copy"] & C["GitHub copy"] & D["Source digest"]

Loading

High-Level Assessment

The chosen approach is optimal: preserve the existing instruction, remove only the non-canonical label, add an explicit final-line anchor, and keep all distributed copies and generated metadata synchronized. Introducing a new field or restructuring the brief would diverge from AGENTS.md’s required template without adding value.

Files changed (4) +7 / -7

Bug fix (1) +2 / -2

SKILL.mdRestore the canonical unlabeled closing instruction+2/-2

Restore the canonical unlabeled closing instruction

• Removes the invented 'Close:' key from the strict-review delegation brief. Clarifies that the unresolved-rule sentence must be quoted as the brief’s own final line.

.agents/skills/local-strict-review/SKILL.md

Documentation (2) +4 / -4

SKILL.mdSynchronize the Claude plugin skill wording+2/-2

Synchronize the Claude plugin skill wording

• Applies the canonical unlabeled closing instruction and final-line clarification to the Claude plugin copy.

.claude-plugin/fleet-skills/skills/local-strict-review/SKILL.md

SKILL.mdSynchronize the GitHub skill wording+2/-2

Synchronize the GitHub skill wording

• Applies the canonical unlabeled closing instruction and final-line clarification to the GitHub-distributed copy.

.github/skills/local-strict-review/SKILL.md

Other (1) +1 / -1

.source-digestRefresh the plugin source digest+1/-1

Refresh the plugin source digest

• Updates the generated digest to reflect the synchronized local strict-review skill content.

.claude-plugin/fleet-skills/.source-digest

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Organization UI

Review profile: ASSERTIVE

Plan: Pro Plus

Run ID: 267adb50-2f60-4f8e-bbfa-092ebfa322b2

📥 Commits

Reviewing files that changed from the base of the PR and between bbc9b8f and 2778010.

📒 Files selected for processing (4)

• .agents/skills/local-strict-review/SKILL.md
• .claude-plugin/fleet-skills/.source-digest
• .claude-plugin/fleet-skills/skills/local-strict-review/SKILL.md
• .github/skills/local-strict-review/SKILL.md

Included review availability: Your plan provides up to 10 included reviews per hour; 1 remains after this review.

---

📝 Walkthrough

Walkthrough

The strict review skill instructions now require the AGENTS.md unresolved-rule line as the final prompt line. The corresponding source digest is updated.

Changes

Strict review prompt alignment

Layer / File(s)	Summary
Final-line instruction and source digest .agents/skills/local-strict-review/SKILL.md, .claude-plugin/fleet-skills/skills/local-strict-review/SKILL.md, .github/skills/local-strict-review/SKILL.md, .claude-plugin/fleet-skills/.source-digest	The three strict review prompts now require the quoted AGENTS.md unresolved-rule line as the final line. The stored source digest uses the new hash value.

Estimated code review effort: 1 (Trivial) | ~3 minutes

Merge Risk:⚪ Minimal · up to 27780

This change only restores the documented unlabeled closing-line format across the synchronized skill files; no actionable merge-blocking risk remains after normal checks and review.

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 0…
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly summarizes the main change: removing the Close: field and matching the unlabeled trailing sentence structure in AGENTS.md.

Full details: Docstring Coverage

Explanation

No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 0 files. (4 skipped: 4 unsupported.)

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch feature/1070-round3-unlabeled-close

---

_{Comment @coderabbitai help to get the list of available commands.}

[qodo-code-review]

Code Review by Qodo

🐞 Bugs (0)📘 Rule violations (0)📎 Requirement gaps (0)

Great, no issues found!

Qodo reviewed your code and found no material issues that require review

Tip of the day

💡 Did you know, you can group findings by type and pick your Finding display, from Minimal to Full

More tips ↗ | Customize Qodo ↗ | Qodo docs ↗

[Copilot]

🟡 Changes recommended

The new unlabeled trailing line in the fenced subagent-brief reads like subagent-facing content but is assembly-time guidance, reintroducing ambiguity the prior Close: label mitigated.

Once you've addressed the issues Copilot identified, you can request another Copilot review.

Pull request overview

This PR updates the local-strict-review skill’s subagent-brief template to remove the Close: labeled field and return to the AGENTS.md-style shape of five labeled fields followed by a single unlabeled trailing line, propagating the change across the mirrored skill distributions and updating the source digest.

Changes:

• Replaced the Close: field with an unlabeled trailing instruction line in the subagent-brief template.
• Applied the same template change to the .agents/, .github/, and .claude-plugin/ skill copies.
• Updated .claude-plugin/fleet-skills/.source-digest to reflect the regenerated distribution.

File summaries

File	Description
.agents/skills/local-strict-review/SKILL.md	Drops the Close: label and rewrites the template’s trailing line.
.github/skills/local-strict-review/SKILL.md	Mirrors the same template update for GitHub skill distribution.
.claude-plugin/fleet-skills/skills/local-strict-review/SKILL.md	Mirrors the same template update for Claude plugin distribution.
.claude-plugin/fleet-skills/.source-digest	Updates the distribution digest after the content change.

Review details

• Files reviewed: 4/4 changed files
• Comments generated: 3
• Review effort level: Lite

---

💡 Configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

[Copilot]

🟡 Changes recommended

The updated placeholder text does not include the “as this brief's own final line” anchor described in the PR, creating a concrete mismatch between the documented intent and the actual template text.

Once you've addressed the issues Copilot identified, you can request another Copilot review.

Review details

• Files reviewed: 4/4 changed files
• Comments generated: 3
• Review effort level: Lite