Skip to content
Skills Library
AI & agents · Automation

subtask4llm-codex

/subtask4llm-codex

Execute a multi-step software change through separate, sequential Codex workers with bounded retries and detailed, relevant handoffs. Use when the user explicitly invokes $subtask4llm-codex or asks to carry out a dependency-ordered implementation plan with isolated worker contexts; do not use for planning-only requests or simple tasks that one Codex can complete directly.

Repository
subtask4llm ↗
Licence
MIT
Last repository change
09.11.2026

Assessment and security

98/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene13 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
5
Scripts
2
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 09.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 2 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: scripts/run_workflow.py, tests/test_run_workflow.py

What it does and when to use it

Execute a multi-step software change through separate, sequential Codex workers with bounded retries and detailed, relevant handoffs. Use when the user explicitly invokes $subtask4llm-codex or asks to carry out a dependency-ordered implementation plan with isolated worker contexts; do not use for planning-only requests or simple tasks that one Codex can complete directly.

Original author description

Execute a multi-step software change through separate, sequential Codex workers with bounded retries and detailed, relevant handoffs. Use when the user explicitly invokes $subtask4llm-codex or asks to carry out a dependency-ordered implementation plan with isolated worker contexts; do not use for planning-only requests or simple tasks that one Codex can complete directly.

How it works

  1. Workflow
  2. Invariants
Original SKILL.md headings · 50 lines, 1,132 words
SKILL.md preview
---
name: subtask4llm-codex
description: Execute a multi-step software change through separate, sequential Codex workers with bounded retries and detailed, relevant handoffs. Use when the user explicitly invokes $subtask4llm-codex or asks to carry out a dependency-ordered implementation plan with isolated worker contexts; do not use for planning-only requests or simple tasks that one Codex can complete directly.
---

# Subtask4LLM

Use the current Codex as the planner and reviewer. Delegate implementation steps to fresh `codex exec` workers through `scripts/run_workflow.py`.

## Workflow

1. Confirm this is a multi-step task whose ordered handoffs justify separate contexts. Do not decompose a small change merely to use the skill.
2. Inspect the repository and convert the authorized work into 2–10 concrete steps. Each step must have a bounded task, observable acceptance criteria, and only earlier steps as dependencies. Treat each worker as having no access to the planner's conversation: put relevant user requirements, decisions, repository findings, file paths, architecture, constraints, edge cases, and implementation guidance into the plan. Use shared `context` for information that applies across steps and each step's `context` for details specific to that step. Include enough detail that the worker can act without guessing; do not rely on unstated conversation context.
3. Read [references/plan-format.md](references/plan-format.md), create a version 1 JSON plan in a temporary location, and validate it with `--dry-run` before execution.
4. Use the current Codex session's model for workers by default, and pass it with `--model` when its exact ID is available. Honor `CODEX_WORKFLOW_MODEL` when the user has explicitly configured it. If neither is available, omit `--model`; Codex CLI will use its configured model. Do not ask the user to choose a model and do not guess a model ID. Choose a different worker model only when the user explicitly requests one or has stated a cost/quality preference that calls for it. Do not upgrade to a stronger model based on your own judgment.
5. Before launching any worker, show the user the plan in a concise, readable form in the conversation: the goal and the ordered list of step titles with a short description and dependencies. Then launch the workflow immediately; do not wait for confirmation. The user can interrupt it or send a follow-up comment while it runs. The current Codex is the planner and reviewer, not an implementation worker: do not edit target source files. It may create only the temporary JSON plan needed to launch the workflow. If a genuinely required detail blocks the plan, ask one concise question and stop; do not make implementation edits while awaiting an answer.
6. Run the orchestrator from the target repository:

   On macOS or Linux, run:

   ```bash
   python3 <skill-path>/scripts/run_workflow.py <plan.json> --workspace <repository>
   ```

   On Windows PowerShell, run:

   ```powershell
   py -3 <skill-path>\scripts\run_workflow.py <plan.json> --workspace <repository>
   ```

   Omit `--model` to use the model configured for Codex CLI. Add `--model <worker-model>` only when the model ID is known and should override that configuration.

   Add `--artifacts-dir <directory>` when persistent prompts, worker results, and diagnostics are useful. Those artifacts can contain task details, dependency summaries, and command output, so treat them as potentially sensitive. Otherwise the orchestrator keeps only its compact final report.
   By default, the runner stops after a step remains unsuccessful after its allowed attempts. Add `--continue-on-error` only when the user wants later steps to run anyway; the final workflow status still reports failure if any step failed.
   The runner streams readable summaries from every subtask and the orchestrator into one workflow-wide live log; it does not create per-attempt progress log files. It prints the log path and a ready-to-copy `tail -f` command when the run starts; use `--live-log <path>` to choose another path. The default live log is outside the workspace in the system temp directory. The log includes tool commands and short output or assistant-response summaries, so treat it as potentially sensitive. It checks progress every 10 minutes, stops a shell command that has produced no update for 10 minutes, and gives the first attempt a 30-minute hard limit. If the first attempt fails and a retry is available, the second attempt gets twice the configured hard limit (60 minutes by default). Adjust the first-attempt limit or checkpoint interval with `--timeout-seconds` and `--timeout-checkpoint-seconds`. Timeout diagnostics include recent activity and a timeout can use the configured retry.
   The live log is for the user to follow. Once the runner starts, show the user its log path and `tail -f` command, then wait for the runner process to finish. Do not repeatedly poll the process, run separate `sleep`/`tail` checks, reread the live log, or send timed progress updates. Check progress again only if the user asks or troubleshooting requires it. The runner's own process supervision and log writes continue while you wait.
   The orchestrator launches each worker with `--yolo`, as requested for this workflow.
7. If the user asks to stop while the workflow is running, interrupt it promptly. If the user sends a follow-up comment, acknowledge it and incorporate it into the remaining work where possible. Any failed attempt, including a timeout or detected stalled command, can use the orchestrator's single retry. The second attempt gets twice the configured hard runtime limit. By default, the runner stops after the last allowed attempt fails; with `--continue-on-error`, it runs the remaining planned steps itself. Do not improvise additional child runs after the runner exits.
8. Review the final report and the actual workspace diff. Run or inspect proportionate final verification before claiming the user's task is complete. Report results, changed files, checks, and unresolved risks without reproducing child transcripts.

## Invariants

- Workers run one at a time in the same workspace, each in a fresh ephemeral Codex session.
- A worker receives the shared project context, the full workflow map, its detailed task and step context, acceptance criteria, and detailed results only from dependencies named in its plan step. Dependency results have a configurable character cap; keep important requirements and design decisions in the uncapped plan context fields.
- The orchestrator disables this exact skill for every child, sets `CODEX_WORKFLOW_CHILD=1` and `CODEX_WORKFLOW_DEPTH=1`, and refuses to run when either guard identifies a child.
- Child prompts forbid launching Codex, subagents, or this orchestrator. Do not weaken those controls.
- Workers run with `--yolo`, which disables Codex sandboxing and approval prompts. Use this workflow only in an externally isolated environment; workers can access files and network resources beyond the workspace.
- Preserve unrelated user changes. Do not add destructive actions, external publication, credential use, or other authority that the original request did not grant.
- Reserve automatic retries for local, repeatable repository work. A failed attempt may leave partial edits for its retry; the orchestrator never resets or rolls back the workspace. Do not delegate deployments, publications, messages, migrations, purchases, or other non-idempotent external effects to this workflow.
- Do not start two workflows in the same workspace concurrently.
- Treat child summaries as evidence to verify, not as proof by themselves.

The guard prevents accidental recursion through this workflow. It is not an operating-system security boundary: a child able to clear its environment and execute arbitrary programs could launch another `codex` process. Strong prevention requires an external sandbox, executable allowlist, or wrapper policy.
Files in this package (5)
  • SKILL.md 8 KB
  • agents/openai.yaml 1 KB
  • references/plan-format.md 7 KB
  • scripts/run_workflow.py 50 KB
  • tests/test_run_workflow.py 12 KB

Versions

The database has no other skills named subtask4llm-codex.

Database snapshot: 13.11.2026 · package version a02a2847d505 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 98subtask4llm-pi
    Plan and run a dependency-ordered software change through sequential, one-shot Pi workers with bounded retries and explicit dependency handoffs. Use for authorized multi-step implementation work that benefits from isolated worker contexts; avoid it for planning-only requests or…
  • 100engineering-workflow
    Use for harness engineering, verification loop design, task dependency graph planning, and multi-step work that needs explicit checks, bounded retries, independent review, or a handoff. Skip for simple questions and isolated edits unless explicitly invoked.
  • 82codex-handoff
    交接当前工作到新 Codex 任务。
  • 100background-implementer
    Run bounded parallel implementation with isolated workers (native worktrees or Codex), respect a dependency DAG, and verify each worker's diff before integrating. Use only when the user explicitly requests background, parallel, or multi-agent implementation, such as "백그라운드 구현",…
  • 90codex-delegate
    DeepSeek Harness 的 Codex 委派模式:输入框下方的 Codex 开关打开后,当前会话的编码需求由 Codex 理解、写实现提示词,再经 dsh-baton 交给 Harness 子会话执行并验收。用户问「Codex 开关怎么用 / 为什么没生效 / 怎么省 token / 让 Codex 动脑 DeepSeek 动手」时读本技能。
  • 96hoyeon-execute
    Hoyeon execution workflow for Codex. Use when the user invokes "$hoyeon-execute" or wants to execute a Hoyeon plan.json through the Bash-first Codex adapter. This adapter loads the canonical execute skill and follows its Codex runtime surface.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.