Help agents make decisions that reflect the user's judgment and continuously identify and address gaps between their work and the user's expectations.
Alignment is an essential part of working with AI. It deserves a dedicated document because expectations differ between users and evolve over time.
ALIGN.md holds the user's current goals, priorities, preferences, constraints, and decision criteria.
Keep these separate from harness configuration and general agent instructions. AGENTS.md should explain when and how to use ALIGN.md, while ALIGN.md remains the source of alignment criteria.
Focus initially on alignment between an individual user and their agents. Multi-user agreements and conflict resolution are outside the initial scope.
Provide an easy-to-use skill that works across new and existing projects. Make it discoverable through relevant skill directories and distribution services, verifying support and registration status rather than assuming universal coverage.
- Agents make decisions consistent with the user's stated criteria.
- Agents notice meaningful misalignment and propose corrections.
- Users spend less effort repeating expectations and correcting avoidable misunderstandings.
- The skill is easy to discover, adopt, and use.
- Ask only consequential, unresolved questions.
- Distinguish confirmed expectations from assumptions.
- Adjust autonomously within existing agreements.
- Reflect lasting changes when the user's intent is clear.
- Do not turn one-off exceptions into permanent preferences.
- Never rewrite agreements to justify an agent's own results.
- Continue independent work while a decision awaits clarification.
Check whether the target project uses Git.
Keep only current alignment criteria in ALIGN.md. When Git is available, use its history to track changes instead of maintaining a separate alignment log.
If Git is unavailable, explain the history limitation. Do not initialize Git or create an alternative history file without a user request.
Review available changes since the last alignment for meaningful drift or new criteria. Do not repeat resolved questions without new evidence.
Record the last full alignment time only after the user confirms the document. Record partial confirmations separately without implying a full review.
- Write repository documentation in English.
- Do not use em dashes or emoji.
- Keep the README brief, with a centered title, useful badges, and a copyable installation request.
- Publish the project publicly under the MIT License.
User-requested scope update recorded: 2026-10-14 (Asia/Seoul). This is a partial update, not a full reconfirmation.
Distribute the alignment method as a maintained skill. README and site copy should guide users to install it, rather than preserving a standalone interview prompt. Support native plugin updates where verified and a user-authorized, targeted refresh at alignment-session start elsewhere. Keep method updates separate from personal criteria and never promise universal background updates.
Suggest focused alignment after consequential judgment mismatches, repeated corrections that reveal missing criteria, and when users are unsure of direction. Before long autonomous runs, propose hypothetical scenarios for uncovered trade-offs and stopping boundaries. Fix clear errors without an interview. Make reflection an available habit, without imposing diaries or reminders.
Check the primary CLI at setup and whether it is the current client. Keep its native instruction file canonical, safely linking other compatible entrypoints when needed. Preserve distinct and nested instructions. Record the skill's invocation and update policy in project ALIGN.md documents.
User-confirmed scope update: 2026-10-15 (Asia/Seoul). Partial confirmation only.
Support full paginated PR feedback collection and recent-first review. Offer accessible project conversations, including supported Codex and Claude records, as optional evidence. Show sources, scope and estimated retrieval/analysis time before collection; reuse the user's choice and refine estimates as work proceeds.
Use taste invariants during self-alignment: scoped, revisable criteria supported by the user's decisions across situations. Examine exceptions and conflicting evidence. Do not infer immutable personality traits, treat team feedback as personal consent, or promote repetition into an agreement. Keep the maintained method in the skill and confirmed current criteria in ALIGN.md.
Primary client: Codex. Canonical instruction file: AGENTS.md.
Use $align, or ask “Use the align skill to review this project's ALIGN.md.”
This development repository discovers its local skill through
.agents/skills/align, linked to skills/align. Method changes are maintained
in this repository's Git history; do not install a second plugin copy here or
automatically pull over local development changes.
Source and user installation guide: https://github.com/hmmhmmhm/align.md .
Last aligned: 2026-10-12 09:24 (Asia/Seoul).