Skip to content

Codex Starter Kit v0.1.1

Choose a tag to compare

View all tags
@VKirill VKirill released this 13 May 20:47
· 6 commits to main since this release
v0.1.1
febd7a7

Codex Starter Kit v0.1.1

RU

Этот релиз переводит starter kit ближе к handoff-режиму работы Codex: меньше лишних вопросов, понятнее intake, безопаснее автоматизация и лучше маршрутизация обычных пользовательских сообщений.

Главное

  • Полностью переработан agents_orchestrator под Codex handoff: intake scoring, task ledger, inline-first workflow, поиск shared root causes, review/verification loop и subagents только при явном разрешении.
  • Добавлен UserPromptSubmit hook handoff-intake-classifier.py для классификации пользовательских сообщений: question-only, analysis, planning, implementation, continue и execute-approved-plan.
  • Intake classifier теперь включается только при наличии private-файла ~/.codex/private/handoff-classifier.env; без него hook молча no-op и не влияет на Codex.
  • Добавлен optional LLM fallback через private env (OPENAI_API_KEY, HANDOFF_CLASSIFIER_MODEL, HANDOFF_CLASSIFIER_LLM) с fail-open поведением, таймаутом и без записи секретов в repo.
  • PostToolUse hook теперь подсказывает self-review после git diff и verification-команд, чтобы Codex сверял изменения с task ledger и явно называл непроверенные риски.
  • templates/AGENTS.md усилен handoff intake scoring и task-ledger правилами.
  • Глобальные hooks и AGENTS.md синхронизированы с новой handoff-моделью.
  • Добавлен ru-text skill и переносимый cross-link из copywriter; создан copywriter agent.
  • README EN/RU обновлены под новые hooks, prompt classification, ru-text/copywriter и handoff workflow.

Безопасность

  • Prompt classifier не активируется без пользовательского private-файла.
  • Private env не входит в repo и не должен попадать в git.
  • Dangerous shell guard продолжает блокировать destructive flows: git reset --hard, git clean, force push, npm audit fix, destructive Docker/systemd/database operations и mutating HTTP requests.

Проверка

  • python3 scripts/validate-pack.py прошёл.
  • Smoke tests classifier hook: no-op без private-файла, deterministic mode, LLM fallback через private env.
  • Установленный ~/.codex/hooks.json проверен на наличие UserPromptSubmit, PermissionRequest, PreToolUse, PostToolUse.

EN

This release moves the starter kit closer to a handoff-style Codex workflow: fewer routine prompts, clearer intake, safer automation, and better routing for normal conversational user messages.

Highlights

  • Reworked agents_orchestrator for Codex handoff: intake scoring, task ledger, inline-first workflow, shared-root-cause discovery, review/verification loop, and subagents only when explicitly authorized.
  • Added the UserPromptSubmit hook handoff-intake-classifier.py for classifying user prompts into question-only, analysis, planning, implementation, continue, and execute-approved-plan modes.
  • The intake classifier now runs only when the private file ~/.codex/private/handoff-classifier.env exists; without it, the hook is a silent no-op and does not affect Codex.
  • Added optional LLM fallback through private env (OPENAI_API_KEY, HANDOFF_CLASSIFIER_MODEL, HANDOFF_CLASSIFIER_LLM) with fail-open behavior, timeout handling, and no secrets committed to the repo.
  • PostToolUse now nudges self-review after git diff and verification commands so Codex maps changes back to the task ledger and reports unverified risk.
  • Strengthened templates/AGENTS.md with handoff intake scoring and task-ledger rules.
  • Synced global hooks and AGENTS.md with the new handoff model.
  • Added the ru-text skill, portable cross-linking from copywriter, and a dedicated copywriter agent.
  • Updated README EN/RU for the new hooks, prompt classification, ru-text/copywriter, and handoff workflow.

Safety

  • Prompt classification is disabled unless the user creates the private config file.
  • The private env file is not part of the repo and must not be committed.
  • The dangerous shell guard still blocks destructive flows such as git reset --hard, git clean, force pushes, npm audit fix, destructive Docker/systemd/database operations, and mutating HTTP requests.

Verification

  • python3 scripts/validate-pack.py passed.
  • Classifier hook smoke-tested: no-op without private file, deterministic mode, and LLM fallback through private env.
  • Installed ~/.codex/hooks.json checked for UserPromptSubmit, PermissionRequest, PreToolUse, and PostToolUse.
Assets 2
Loading