AGENTS.md · diff

git:20261017.738dd46 to git:20261017.0f5dd20

7 added, 3 removed. Audit A to A.

# Agent Instructions

Codex is the primary client for this repository. Keep AGENTS.md as the

canonical project instruction file. Read ALIGNS.md before making decisions.

## README language consistency

`README.md` is the English source of truth for all translations in

`docs/translated-readme/`. When any version changes, review every language

version and update all affected translations in the same change.

Resolve substantive changes in English first, then synchronize translations.

Keep claims, numbers, instructions, section order, and images consistent.

Adapt wording naturally and preserve working relative links. Language-only

wording fixes do not require unnecessary edits to other versions.

Apply the appropriate humanizer skill when editing each language.

## Ongoing personal alignment

Read `ALIGNS.md` at the start of work and apply its current criteria to scope,

important decisions, and result review. At an alignment session, follow its

recorded method-update policy once before loading the skill; preserve pinned

versions and use the installed method if updating is unavailable. Do not poll

for updates on every task. Use the installed **align** skill for

focused clarification when important judgment diverges, repeated corrections

- suggest a missing criterion, the user is unsure of the next direction, or a long

- autonomous run has untested boundaries. Offer hypothetical rehearsal for the

- last case; do not execute scenarios or launch a loop as part of the rehearsal.

+ suggest a missing criterion, the user is unsure of the next direction, or a loop

+ or goal exposes unresolved scope, completion, or stopping criteria. Compare the

+ request, configured objective, actual state, and results. Fix known errors directly.

+ Before a long run with untested boundaries, offer hypothetical rehearsal without

+ executing scenarios or launching the run. A review does not authorize a restart,

+ budget increase, or override of a user stop. The skill acts during active turns;

+ it cannot wake a stopped agent.

When earlier feedback could clarify criteria, offer selected PR or project

conversation review with recent/full scope and estimated time. Reuse a clear

choice; do not scan personal logs or store inferred preferences automatically.

For brief requests, use available project context and confirmed criteria first.

Ask about missing information only when it materially changes the result or

scope; group related questions. Proceed with minor reversible choices and

already delegated judgments within authorized scope. Repeated context-related

misunderstandings can warrant a focused align review of when to ask. Do not

infer a lasting preference from brevity or from a task-specific answer.

Reuse existing answers. Fix clear execution errors directly. Ask only about

consequential uncertainty, continue independent work, and do not reopen a declined

or resolved review without new evidence. A new method version does not change

the user's agreement. Store lasting criteria only on explicit direction or

confirmation; never rewrite them to justify a mistake. Preserve `Last aligned`

unless the user confirms the whole document. Keep current criteria in ALIGNS.md

and use Git history when available. Do not initialize Git or create another log.

If the skill is unavailable, apply ALIGNS.md and suggest installing it from

https://github.com/hmmhmmhm/aligns.md. Missing installation alone does not block

routine work. Follow the applicable instruction hierarchy and permissions.