Skip to content

docs(aidd-context): reduce cognitive load in agents instructions - #949

Open
alexsoyes wants to merge 2 commits into
nextfrom
codex/agents-cognitive-load
Open

alexsoyes wants to merge 2 commits into
nextfrom
codex/agents-cognitive-load

Conversation

@alexsoyes

@alexsoyes alexsoyes commented Oct 1, 2026 •

Copy link
Copy Markdown
Contributor

🎯 What & why

Reduce the reader's cognitive load in the shared AGENTS.md template: reason and prioritize before replying, then lead with the result or recommendation.

🛠️ How it works

  • Condense overlapping instructions while preserving evidence, safety, and explicit Git authorization.
  • Make memory loading, batching, and delegation task-dependent; address frustration before offering compaction.
  • Scope: the project-memory template only, not existing project AGENTS.md files.

🧪 How to verify

  • git diff --check: passed.
  • Pre-commit checks: 441 tests passed.
  • Pre-push checks: knip passed; 5,440 CLI tests passed across 451 files.

✅ I certify

  • I DO CERTIFY I READ EACH LINE OF THE PULL REQUEST BECAUSE I AM A SOFTWARE ENGINEER, NOT A AI PUPPY.

Keep generated project instructions concise and context-aware. Prefer high-signal bullets, remove test-only greeting and full-memory fallback, and batch work only when it saves time or context.
Prioritize recommendations and surface only what the reader needs to understand or act. Keep instructions concise and offer compaction only after addressing frustration.
@alexsoyes
alexsoyes marked this pull request as ready for review October 1, 2026 03:26
@alexsoyes
alexsoyes requested a review from a team as a code owner October 1, 2026 03:26
@alexsoyes
alexsoyes enabled auto-merge October 1, 2026 03:26
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants