Skip to content

New Project Codex Prompt

Use this prompt when you already have:

  • a local project folder;
  • a project goal document;
  • a Codex session with access to that folder.

Replace the placeholders before sending it to Codex.

CLI Generator

Generate the current handoff prompt locally:

loopx new-project-prompt \
  --project <PROJECT_ROOT> \
  --goal-doc <GOAL_DOC_PATH>

If the project needs a controller that can split scoped sub-agent probes:

loopx new-project-prompt \
  --project <PROJECT_ROOT> \
  --goal-doc <GOAL_DOC_PATH> \
  --spawn-allowed \
  --allowed-domain docs-map \
  --allowed-domain validation-map \
  --write-scope "docs/**"

Copy-Paste Prompt

Use the CLI output as the setup instructions; it is the maintained prompt owner. The following request asks Codex to generate and follow that current output:

请将当前项目接入 LoopX。先读取目标文档，再运行：
loopx new-project-prompt --project <PROJECT_ROOT> --goal-doc <GOAL_DOC_PATH>
按本机当前版本生成的 prompt 完成接入、验证和读回。
保留现有 Goal/Agent 身份和授权；接入成功不等于交付完成。
首次接入只登记目标和状态，不生成首连 onboarding todo；先核对候选 Todo，
得到所需确认再开始 delivery。已有授权覆盖的后续动作不重复请示。

The generated prompt checks the current guard before autonomous work and follows interaction_contract.cli_channel.settlement_plan.ordered_steps or current next_cli_actions after validation. It preserves exact Turn/effect identities, actual outcomes, failed/unknown readback, authorization and explicit stop gates. For recurring execution, generate the host-specific --bootstrap loader; do not save a static execution body or reconstruct refresh/spend from this guide.

Continue a selected outcome through implementation, integration, negative cases and readback while authorized work remains feasible. Keep recovery evidence and the next action in existing state; a call, receipt or setup step is not completion. Notification suppression is independent of admission to work. A missing authority gates the dependent path; it cannot grant permission to that path or silently cancel independent admitted work.

Use configure-goal for incremental scope changes. Rebuilding with bootstrap --force requires explicit user direction; use --preserve-todos when existing state/Todos must survive. Sub-agent settings only describe the approved scope; they do not grant spawn permission. Runtime helpers, private state and generated logs stay out of public artifacts.

Minimal Command

If the goal is simple and does not need a project-specific adapter yet:

cd <PROJECT_ROOT>
loopx connect \
  --goal-id <STABLE_GOAL_ID> \
  --objective "<OBJECTIVE_FROM_GOAL_DOC>" \
  --domain <DOMAIN> \
  --goal-doc <GOAL_DOC_PATH>

Then inspect:

loopx registry
loopx status
loopx check --scan-root .

What Good Looks Like

The first connection is successful when:

  • the project has a stable ACTIVE_GOAL_STATE.md;
  • the registry points to that state file;
  • the goal appears in loopx status;
  • the attention queue says exactly who should act next;
  • private evidence is kept in the project or local runtime, not in public docs;
  • the next Codex tick can continue from saved state instead of re-reading the whole conversation.

For larger projects, the first useful adapter is usually read-only. It should map documents, TODOs, validation surfaces, risks, and handoff packets before it edits files.