Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/alexzh3/codex-orchestrator/orchestratenpx skills add alexzh3/codex-orchestrator --skill orchestrategit clone --depth 1 https://github.com/alexzh3/codex-orchestratorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alexzh3/codex-orchestrator/orchestrate)<a href="https://agentmods.dev/skills/alexzh3/codex-orchestrator/orchestrate"><img src="https://agentmods.dev/badge/skills/alexzh3/codex-orchestrator/orchestrate.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00025 | $0.00659 |
| Opus 5 | $0.00013 | $0.00329 |
| Sonnet 5 | $0.00005 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
codex-orchestrator-orchestrate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude-Codex Orchestration
Claude coordinates and verifies focused agent work. Codex handles scoped implementation and review through its native CLI. Prefer Codex as the first mover for bounded coding tasks.
Use this skill for one focused agent cycle inside an orchestration run. The workflow skill owns planning, run initialization, task decomposition, closure, and reporting. Return to it when the focused phase is complete.
Durable Run
Keep run material under:
.codex-orchestrator/runs/<run-id>/
journal.jsonl
<provider>-<role>-<NN>/execution-<NN>/
prompt.md
events.jsonl
handoff.md
evidence/ # optional
report.md # after run_closed
journal.jsonl is Claude's append-only orchestration journal. Read
${CLAUDE_PLUGIN_ROOT}/docs/orchestration-contract.md before creating or interpreting journal
entries; it owns record fields, authority, validation, and closure semantics.
Capture each execution's exact prompt, raw events when available, and exact handoff. Never
synthesize a log or rewrite a handoff. Keep small observations inline and create evidence/ only
when material output must be retained.
Focused Agent Cycle
- Read the complete journal, current task, and relevant references before acting.
- Confirm the task's acceptance criteria and allowed/owned
files. - Compare active task files and shared resources before parallel work; serialize overlap or use a worktree.
- Reuse a relevant agent or create a named one. For an independent review, start a fresh agent and native session.
- Resolve the execution's absolute worktree, full HEAD, and attached branch when present and
include them in its record. Save the exact prompt and append
executionbefore launch. - Monitor with the bundled tools without editing files owned by the active agent.
- Save the exact handoff, inspect it and the repository, then append terminal
execution_result. - Evaluate acceptance criteria and record material checks as
verification. - Record only consequential resolutions or user dependencies as
decision. - After evaluating the criteria, append
completewhen they are satisfied,failedwhen they are conclusively unmet and no in-scope recovery remains, orblockedwhen a user or external dependency prevents completion or judgment. Otherwise keep the taskactiveand return the unresolved work to the workflow.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 69 lines · 25 tokens per session scan A 5e2c8216629a
codex-orchestrator-orchestrate is a skill published in the GitHub repository alexzh3/codex-orchestrator (84 stars, last pushed 26d ago), licensed MIT. It adds 25 tokens to every session and 659 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…