Borrowing it
Nothing to install: this file belongs to DeL-TaiseiOzaki/claude-code-orchestra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DeL-TaiseiOzaki/claude-code-orchestra/main/.claude/skills/codex-system/SKILL.mdgit clone --depth 1 https://github.com/DeL-TaiseiOzaki/claude-code-orchestraWrote 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/del-taiseiozaki/claude-code-orchestra/codex-system)<a href="https://agentmods.dev/skills/del-taiseiozaki/claude-code-orchestra/codex-system"><img src="https://agentmods.dev/badge/skills/del-taiseiozaki/claude-code-orchestra/codex-system/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/del-taiseiozaki/claude-code-orchestra/codex-system"><img src="https://agentmods.dev/badge/skills/del-taiseiozaki/claude-code-orchestra/codex-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Excessive Agency · line 254 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Excessive Agency · line 49 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 5.1 | $0.00089 | $0.04035 |
| Opus 5.5 | $0.00036 | $0.01614 |
| Sonnet 5.5 | $0.00018 | $0.00807 |
| Haiku 4.5 | $0.00009 | $0.00404 |
Grade A, and why
codex-system 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 1mo 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex System — Planning, Design & Complex Implementation
Codex CLI handles planning, design, and complex code implementation.
Preflight (SSOT): Update CLIs before each session —
claude update && npm install -g @openai/codex@latest. Releases drift frequently (model names, flags, sandbox semantics). Other skills reference this line instead of repeating it. Delegation policy (when to delegate):.claude/rules/codex-delegation.md
Two Roles of Codex
1. Planning & Design
- Architecture design, module composition
- Implementation plan creation (step breakdown, dependency ordering)
- Trade-off evaluation, technology selection
- Code review (quality and correctness analysis)
2. Complex Implementation
- Complex algorithms, optimization
- Debugging with unknown root causes
- Advanced refactoring
- Multi-step implementation tasks
When to Delegate
Delegation policy — when to consult, when NOT to, and trigger criteria — lives in .claude/rules/codex-delegation.md (SSOT). This skill covers how to consult. The other half of "how" is how to verify what came back: root AGENTS.md → Guardrails (Completion Verification) is mandatory for every write-access call, and Verify Before Trusting below is its executable form. A delegated CLI is never trusted on its self-report.
How to Consult
Invoke Codex through the wrapper —
.claude/skills/_shared/codex_consult.py— instead of callingcodex execdirectly.codex execitself waits for stdin EOF and hangs indefinitely when stdin is left open (e.g. background shells); the wrapper always runs it with stdin closed, so callers never need< /dev/null. It also passes the prompt as a single argv element (no shell, so nested quotes in the prompt body never break it), captures stdout/stderr to timestamped files under.claude/logs/codex/, and reports one JSON result instead of silently discarding stderr.
python3 .claude/skills/_shared/codex_consult.py (--prompt-file PATH | --prompt-stdin) [--label L] [--caller AGENT] [--sandbox {read-only,workspace-write,danger-full-access}] [--model M] [--timeout N] [--cwd DIR] [--project-root DIR] [--skip-git-repo-check] [--config KEY=VALUE]
What ships with it
5 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.
- 1mo ago Changed e0ddef4d511f
- 1mo ago Changed 6fc2c2a6ecb8
- 2mo ago Changed f2ddba38b221
- 2mo ago First seen · 306 lines · 89 tokens per session scan A 20d2465663a8
codex-system is a skill published in the GitHub repository DeL-TaiseiOzaki/claude-code-orchestra (198 stars, last pushed 5d ago), licensed MIT. It adds 89 tokens to every session and 4,035 once invoked, about $0.0004 per session on Opus 5.5. 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.
codex-system compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| codex-systemDeL-TaiseiOzaki/claude-code-orchestra | Skill | 198 | 5d ago | MIT | A | 89 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |