[instructions] Sync instruction files with release v0.84.2 - #49562
[instructions] Sync instruction files with release v0.84.2#49562github-actions[bot] wants to merge 1 commit into
Conversation
Release/change audit found no schema or safe-output drift since v0.83.4 (latest full release) — the .github/aw/*.md updates already on main (new syntax-engine.md, github-mcp-server-pagination.md, token-optimization-caching-budgets.md split files, bounded-queries, data:, auto-merge method, local skills) all check out against pkg/parser/schemas/main_workflow_schema.json and pkg/workflow/*.go. Remaining work was the duplication audit: trim repeated recompilation-rule and safe-output security-posture text out of github-agentic-workflows.md and update-agentic-workflow.md in favor of the canonical workflow-editing.md and workflow-constraints.md, and remove a persona-example table in github-agentic-workflows.md that duplicated its own Persona-to-Pattern Quick Matrix. Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
This comment has been minimized.
This comment has been minimized.
|
@copilot quick triage for this PR:
|
|
Hey ✅ Clear scope — focused deduplication and sync of The PR is ready for review. All changes align with the project's documentation maintenance standards.
|
|
Caution agentic threat detected DetailsPotential security threats were detected in the agent output. Review the workflow run logs for details. @copilot quick triage for this PR:
|
Summary
Routine instructions-janitor pass over .github/aw/*.md.
Release/change audit
Size audit
All .github/aw/*.md files are under their target limits (largest is designer.md at 392 lines, under 400).
Duplication audit
Found and fixed:
No other meaningful duplication found; other cross-references (e.g. safe-outputs.md in creator/updater/debugger prompts, workflow-constraints.md single-job architecture references in workflow-patterns.md) were already short pointers, not restatements.
Before/after line counts (modified files only)
All three remain well under their target limits (github-agentic-workflows.md < 200, others < 400).
Test plan
Caution
agentic threat detected
Threat detection flagged this output in warn mode. Manual review is REQUIRED before any follow-up automation.
Details
Potential security threats were detected in the agent output.
Review the workflow run logs for details.
Run details: https://github.com/github/gh-aw/actions/runs/30702262954