菜单
Orchestrate read-only Codex research in any mode, or one to eight Codex agents to implement approved plans from Claude Code or Codex CLI.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/PaulRBerg/agent-skills --skill codex-handoff命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Assess recurrence risk for agent behavior using local Codex/Claude Code transcripts and recommend evidence-backed durable fixes to AGENTS.md or skills. Not for routine post-success skill-evolution or agent self-improvement reviews.
Create or polish repo agent context: README.md, AGENTS.md/CLAUDE.md, installed project skills, and other Markdown context docs.
Use for current official documentation about Codex, Codex CLI, or Claude Code behavior, configuration, prompting, skills, permissions, tools, surfaces, capabilities, troubleshooting, hooks, app-server, or hook trust; fetch the relevant official URL before answering.
正在显示 SKILL.md
| argument-hint | [task] |
| compatibility | Requires Plan mode for implementation handoffs, but research-only handoffs may run in any mode. The Claude Code host also requires Git, /bin/bash, Python 3, and an authenticated Codex CLI with dangerous bypass support; the Codex CLI host requires native subagents. |
| disable-model-invocation | true |
| metadata | {"install-targets":"claude-code codex"} |
| name | codex-handoff |
| skill-dependencies | ["agents-brain","code-polish","commit"] |
| user-invocable | true |
| description | Orchestrate read-only Codex research in any mode, or one to eight Codex agents to implement approved plans from Claude Code or Codex CLI. |
Codex-handoff orchestrates read-only investigation in any mode, or implementation within the current session from Plan mode. Task-handoff instead writes a decision-complete file for a fresh, separate session; use it when work continues later or elsewhere, and use an in-session handoff skill to implement an approved plan now.
If these instructions are already present in the conversation from a slash or dollar invocation, follow them directly; do not invoke this skill again through a skill tool.
Follow the shared contract below, select exactly one host adapter, and use it for every host-specific action.
Inspect the callable orchestration tools, not environment variables, process ancestry, or a user-supplied host name:
spawn_agent, wait_agent, send_message, followup_task available: read references/codex-cli-host.md
completely.references/claude-code-host.md completely.Use exactly one adapter for every host-specific action; never load both or combine their launch, progress, retry, permission, or result-transport mechanics. The adapter may specialize host mechanics and manifest configuration but cannot weaken this shared contract.
R1-, counted separately from the eight implementation agents.R3Use $ARGUMENTS as the task when present; otherwise use the active user request.
For a research-only task, launch one to three research agents and stop after returning the consolidated investigation; never enter the Plan Phase or launch implementation agents. For an implementation handoff, trigger research when scope is uncertain, the task crosses multiple or unfamiliar subsystems, or gathering the needed evidence serially would be materially slower for the parent. Zero research agents is the default for implementation handoffs. The parent alone decides the research count from task and repository evidence; never ask the user to opt in or name agents. Either launch the research wave immediately or proceed straight to planning.
When triggered, assign up to three agents stable IDs R1-R3 and launch them immediately through the selected
adapter's read-only mechanism. Give each agent a self-contained prompt containing:
status, findings, open_questions, evidence, and blockers.When every required research agent settles, fold its findings and evidence into the implementation plan or the research-only response. Surface open questions or blockers through the host's user-question mechanism only when they change scope or approach. Do not reconcile the working tree — research agents change nothing; any reported edit is a contract violation.
For a research-only task, synthesize the evidence and finish with ### 🔎 Research handoff — <completed|blocked>, the
agent count, findings, evidence, open questions, and blockers. This replaces the Plan Phase and the selected adapter's
implementation completion report. If the investigation shows that changes are needed, report them as findings and stop —
do not produce an implementation plan or begin edits.
Enter this phase only for an implementation handoff in Plan mode.
Produce a decision-complete plan with this section and the selected adapter's exact manifest table:
## Codex Handoff
- Research: `<none | R1..Rn — key findings used>`
- Strategy: `<sequential|parallel|hybrid>`
- Agents: `<1-8>` — `<why this is the smallest effective count>`
- Validation owner: `<agent-id|parent>` — `<aggregate checks it runs once>`
<host-adapter manifest table>
- Code polish: `<required|not required>` — `<reason>`
- Agent-context polish: `<required|not required>` — `<reason>`
Choose the execution shape from repository evidence and the approved work:
A wave finishes with its slowest agent. Keep the highest-tier agent's scope minimal and move deferrable validation to the validation owner. If parallel work does not collectively prove the overall plan, reserve a later sequential agent for integration and aggregate validation. Use stable agent IDs and explicit dependencies across the whole handoff.
Assign aggregate validation to exactly one owner: package- or repository-wide checks run once, by the integration agent when one exists, otherwise by the parent during post-wave reconciliation. Every other agent runs only the narrowest checks that prove its own edits, such as file-scoped formatting, lint, or typecheck plus targeted tests.
Require $code-polish for nonlocal invariants, concurrency or state machines, migrations or parsing, auth or security,
retry or error semantics, and public API or data-contract changes. File count alone is not a trigger.
Require $agents-brain polish when approved work changes a target its polish workflow supports: README.md, AGENTS.md or
CLAUDE.md, a durable context doc, or an existing project-installed skill under .agents/skills. Source catalog skills
under skills/ stay outside that workflow. Mark both passes required when both trigger rules apply; mark neither when
neither applies.
Do not launch implementation agents until the user approves the plan and the host leaves Plan mode. Read-only research is the only pre-approval exception.
Build a self-contained, outcome-first prompt for every implementation agent. Include:
blocked with partial evidence
rather than grinding past it.blocked.blocked with
evidence instead of proposing a replacement plan.status (completed or blocked), summary, changed_files listing
only files actually touched, verification listing every command and outcome, residual_risks, and blockers.Keep each agent prompt as compact as completeness allows: the shared outcome summary plus that agent's own brief, scope, and constraints — never restate the full plan text per agent.
Add the selected adapter's command, permission, transport, and host-tool constraints without restating this contract.
Launch agents through the selected adapter in the approved strategy and dependency waves. Do not add agents or change models, efforts, scopes, or validation ownership merely because a worker is slow or quiet. Do revise the manifest and launch a narrowly scoped follow-on agent when completed work discovers an unplanned prerequisite covered by the approved outcome. Preserve stable IDs, dependency order, the eight-agent limit, and one aggregate-validation owner; include follow-on agents in the final counts and report.
For each completed agent: require every shared result field and treat changed_files as its authoritative post-pass
scope; confirm reported files exist or were intentionally deleted, stay within scope, and carry verification evidence
matching the assignment; and pass relevant completed results to dependent agents.
After every implementation wave, reconcile all results with the current manifest and visible working tree without folding in unrelated concurrent changes. When the parent owns validation, run the assigned aggregate checks once during this reconciliation. Attribute aggregate-check failures before blocking: a failure confined to files outside every agent's scope is unrelated concurrent work, so confirm the handoff's files still pass and continue. Unexpected out-of-scope edits, same-wave overlap, or a failure attributable to the handoff are blockers; do not start dependents or polish, and do not silently take over implementation.
status: blocked result identifying a related in-repository fix or evidence change outside the worker's scope that
is necessary for the approved outcome is follow-on work under the Contract's scope-expansion authority, not a request
for fresh authorization: let already-started independent agents finish, gate dependents, extend the manifest with the
smallest sufficient scope, satisfy repository coordination for that scope, and launch a new or reused implementation
agent. Repeat until the outcome is complete or a genuine authorization boundary is reached.After every required agent succeeds and the task is verified — never for a blocked, failed, or partial handoff — the
parent alone judges skill-evolution opportunities; agents never make the recommendation. Recommend only a stable,
reusable workflow credibly likely to recur; reject one-offs, rare contingencies, incidental cleanup, and speculative
value. For a new skill, state repo-local vs. global ~/projects/agent-skills placement; for a revision, name the exact
skills and why. When a proposal clears this bar, append at most one compact suggestion (≤2 short sentences) to the
adapter's existing completion report without changing its format, then offer $task-handoff as the next action. Never
auto-invoke $task-handoff or create/revise anything during this review; when nothing qualifies, stay silent — no
placeholder.
changed_files and confirm the combined
verification evidence proves the approved plan.$code-polish first in its default simplify-then-review mode, then
$agents-brain polish with its eligible context targets. Invoke only one when only one is required. Do not seed
either pass with paths outside the union or let it broaden beyond its declared workflow authority.$commit
from each additional repository after its work, validation, and required polish complete. $commit owns semantic
message composition; its ai-commit backend owns deterministic transaction, commit, and push mechanics. Scope each
invocation to files changed there; do not commit incomplete, blocked, unexpected, or out-of-scope changes. Push only
when the user explicitly requested it.none for
applicable empty values and never expose machine result payloads.