skillsFirst-partyReview first Safety · Privacy ·
Codex Automations Orchestrator Capability Pack Skill
Expert automation-orchestration capability pack for designing safe, low-noise recurring Codex workflows with clear runbooks.
by JSONbored·added 2026-04-11·83,749 source repo stars·
Claude CodeCodexWindsurfGeminiCursorCLI
HarnessClaude CodeCodexWindsurfGeminiCursorCLI
Level:expertType:capability-packVerified:validated
Review first — review before installing
Open the source and read safety notes before installing.
Prerequisites
- Automation goals and success metrics
- Notification channel
- Operational owner
Schema details
- Install type
- package
- Reading time
- 9 min
- Difficulty score
- 85
- Troubleshooting
- Yes
- Breaking changes
- No
Source repository stats
- Scope
- Source repo
- Stars
- 83,749 source repo stars
- Forks
- 12,151
- Updated
- 2026-05-19T11:39:05Z
Package metadata
- Package verified
- Yes
- SHA-256
- 7e3ee39f61507d249f0b0b5ec49c35c6fc076b5ca2d6f85174eec8664de00867
Skill and platform metadata
- Skill type
- capability-pack
- Skill level
- expert
- Verification
- validated
- Verified at
- 2026-04-11
Retrieval sources
https://github.com/openai/codexhttps://spec.modelcontextprotocol.io/specification/https://www.rfc-editor.org/rfc/rfc5545
Tested platforms
ClaudeCodexOpenClawCursorWindsurfGemini
| Platform | Support | Install path |
|---|---|---|
| claude-code | Native | .claude/skills/<skill-name>/SKILL.md |
| codex | Native | .agents/skills/<skill-name>/SKILL.md |
| windsurf | Native | .windsurf/skills/<skill-name>/SKILL.md |
| gemini | Native | .gemini/skills/<skill-name>/SKILL.md or .agents/skills/<skill-name>/SKILL.md |
| cursor | Adapter | .cursor/rules/<skill-name>.mdc |
| cli | Manual | AGENTS.md or tool-specific context file |
Full copyable content
# Trigger
"Apply the Codex automations orchestrator capability pack."
# Required output
1) Automation inventory and purpose
2) Schedule/risk matrix
3) Prompt and output contract per automation
4) Alerting and rollback planAbout this resource
Knowledge Freshness
This capability pack is pinned to documentation verified on 2026-04-11.
Retrieval Sources
- https://github.com/openai/codex
- https://spec.modelcontextprotocol.io/specification/
- https://www.rfc-editor.org/rfc/rfc5545
Core Workflow
- Define automation objective and business value.
- Set schedule with explicit risk and blast-radius limits.
- Write self-sufficient prompt with output contract.
- Add observability, alerts, and runbook actions.
- Review periodically and retire low-value automations.
Overview
This skill turns ad-hoc recurring tasks into maintainable automations with clear guardrails and measurable outcomes.
Capability Scope
- Automation scoping and prioritization
- Schedule and RRULE governance
- Prompt reliability for unattended runs
- Alert routing and escalation design
- Lifecycle management and cleanup
Compatibility
Native
- Claude Code / Claude: native skill usage via
SKILL.md. - Codex/OpenAI workflows: compatible with Agent Skills-style
SKILL.mdcontent as reusable workflow instructions.
Manual Adaptation
- Gemini CLI: native skill usage via
.gemini/skills/<skill-name>/SKILL.mdor.agents/skills/<skill-name>/SKILL.mdwhere supported. - Cursor: use the generated
.cursor/rules/*.mdcadapter for project rules. - OpenClaw and similar agents: use the same skill content as a reusable prompt/workflow file when native skill import is unavailable.
Production Rules
- Every automation must declare bounded scope and expected outputs.
- Alert only on actionable failures to avoid fatigue.
- Prevent overlapping destructive runs with single-flight controls.
- Keep runbooks current for pause, rollback, and recovery actions.
Troubleshooting
Issue: Automation output is inconsistent
Fix: tighten prompt to fixed output schema and acceptance checks.
Issue: Too many alerts
Fix: only notify on actionable failures, not informational events.
Issue: Runs overlap and cause drift
Fix: enforce single-flight behavior and lock window policy.
Output Contract
- Automation definition per task.
- Schedule + risk controls.
- Alert routing and runbook.
- Maintenance cadence and retirement triggers.
Content outline
#codex#automation#orchestration#scheduling#capability-pack
Source citations
Signals
Loading live community signals…
More like this, weekly
A short, calm digest of reviewed Claude resources. Unsubscribe any time.