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/kid-sid/codex-spellbook/codex-orchestrationnpx skills add kid-sid/codex-spellbook --skill codex-orchestrationgit clone --depth 1 https://github.com/kid-sid/codex-spellbookWrote 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/kid-sid/codex-spellbook/codex-orchestration)<a href="https://agentmods.dev/skills/kid-sid/codex-spellbook/codex-orchestration"><img src="https://agentmods.dev/badge/skills/kid-sid/codex-spellbook/codex-orchestration.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 | $0.00099 | $0.02537 |
| Opus 5 | $0.00049 | $0.01269 |
| Sonnet 5 | $0.00020 | $0.00507 |
| Haiku 4.5 | $0.00010 | $0.00254 |
Grade D, and why
codex-orchestration scanned grade D with 2 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
# ~/.codex/config.toml Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
if [[ "$1" == *"rm -rf"* ]]; then exit 2; fi How it starts
The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Orchestration
How OpenAI Codex CLI discovers skills, fires hooks, and loads instructions. Use this skill instead of web-searching the docs each time.
Source of truth: developers.openai.com/codex/{skills,hooks,config-advanced,config-reference,guides/agents-md}. Verify against live docs if behavior seems off - orchestration features evolve.
When to Activate
- Install a skill and need the correct target directory
- Wire a Codex hook and need the event name, matcher, or payload shape
- Debug why an implicit skill isn't triggering on a matching prompt
- Author or review
agents/openai.yamlfor a skill - Explain to a teammate why format-on-edit hooks don't work in Codex
- Migrate hook or skill conventions from Claude Code to Codex
- Add a
notifyprogram for turn-complete events - Write or update this repo's README/hooks documentation
Discovery: Skills
Skills are folders containing SKILL.md (required) plus optional scripts/, references/, assets/, and agents/openai.yaml. Codex scans these paths (earlier wins on activation; duplicate names do NOT merge - both appear in selector):
| Priority | Path | Scope |
|---|---|---|
| 1 | $CWD/.agents/skills |
Current folder |
| 2 | $CWD/../.agents/skills |
Parent folder |
| 3 | $REPO_ROOT/.agents/skills |
Repo root |
| 4 | $HOME/.agents/skills |
User |
| 5 | /etc/codex/skills |
Admin |
| 6 | Bundled | System |
Common mistake: copying skills to ~/.codex/skills/ - that path does nothing. Use ~/.agents/skills/.
SKILL.md Format
---
name: kebab-case-name
description: What it does, when to use it, AND when NOT to use it. Codex matches this for implicit invocation.
---
The body loads only after the skill activates. Front-load triggers and scope boundaries in description.
agents/openai.yaml (Optional)
Put it at skills/<name>/agents/openai.yaml:
interface:
display_name: "User-facing name"
short_description: "User-facing description"
icon_small: "./assets/small-logo.svg"
icon_large: "./assets/large-logo.png"
brand_color: "#3B82F6"
default_prompt: "Optional surrounding prompt"
policy:
allow_implicit_invocation: true
dependencies:
tools:
- type: "mcp"
value: "serverName"
description: "Required MCP server"
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.
- 4d ago First seen · 291 lines · 99 tokens per session scan D 4de1d3b6c77c
codex-orchestration is a skill published in the GitHub repository kid-sid/codex-spellbook (21 stars, last pushed 3mo ago), licensed MIT. It adds 99 tokens to every session and 2,537 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…