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/skyloevil/codex-sdd/customizenpx skills add skyloevil/codex-sdd --skill customizegit clone --depth 1 https://github.com/skyloevil/codex-sddWhat 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 | $0.00030 | $0.01364 |
| Opus 5 | $0.00015 | $0.00682 |
| Sonnet 5 | $0.00006 | $0.00273 |
| Haiku 4.5 | $0.00003 | $0.00136 |
Grade A, and why
codex-sdd:customize 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 yesterday.
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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenSpec Customize
Context
Codex SDD is designed to be extensible. Teams can inject custom workflows at key hook points throughout the lifecycle. This skill documents how to extend the plugin with team-specific MCP tools, skills, and scripts.
Extension Points
1. Hook Points in the Workflow
Each phase has well-defined hook points where custom behavior can be injected:
| Phase | Hook Point | Timing | Common Use Cases |
|---|---|---|---|
| propose | pre_proposal | Before generating proposal | Fetch requirements from TAPD/JIRA, clarify with LLM |
| propose | post_confirm_scope | After scope is confirmed | Notify PM, create tracking ticket |
| plan | pre_design | Before design generation | Fetch existing API docs, load codebase context |
| plan | post_confirm_design | After design is approved | Send for team review, update wiki |
| implement | pre_execute_task | Before each task | Run lint, fetch latest code |
| implement | post_complete_task | After each task | Run unit tests, check types |
| validate | pre_validate | Before drift check | Run full test suite |
| validate | post_validate | After validation | Send report, create JIRA subtasks for fixes |
| archive | pre_archive | Before archiving | Generate change log, update release notes |
| archive | post_archive | After archiving | Notify team, sync to knowledge base |
Hooks are business extensions, not control-plane owners. They may provide context, validation, review, notifications, or external synchronization, but the OpenSpec loop state remains the source of truth for phase, goal status, completion, blocked state, and human gates.
Recommended hook policy fields:
hooks:
pre_validate:
- id: run_ci
kind: command
name: npm-test
command: npm test
required: true
mode: auto
timeoutMs: 120000
onFailure: retry_then_human
required: failed or pending result blocks the associated gate.mode:auto,review, ormanual.onFailure:warn,retry_then_human,human_review, orblock.- External writes should default to
reviewormanual.
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.
- yesterday First seen · 167 lines · 30 tokens per session scan A 516b7f7baafe
codex-sdd:customize is a skill published in the GitHub repository skyloevil/codex-sdd (1 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 1,364 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
codexkit-repository-maintenance
Use when maintaining or improving the GameStudio-CodexKIT source repository, including CI, governance, catalog, generators, adapters, packaging, documentation, versioning, or release readiness.
unity-ui-art-and-motion-production
Use when new or revised Unity UI visuals, icons, panels, 9-slice sprites, component states, HUD or menu layouts, popup motion, screen transitions, or flattened UI screenshot decomposition must be produced through Figma and integrated into uGUI, NGUI, or UI Toolkit; not for UI debugging, localization-only work…
game-screenshot-showcase-and-store-packaging
Use when a Unity team needs approved PlayMode screenshots, immutable capture evidence, reviewed showcase slides, or report-only store screenshot packaging without auto-upload, signing, or submission.
studio-project-scaffold
Use when running gamestudio init, status, or uninit, or bootstrapping a new or adopted game repository with AGENTS.md, HANDOFF.md, .agents/CONTRACT.md, project governance, a subsystem registry, or a per-project adapter report, plan digest, named reviewer, backup root, generated agent overlay, apply, uninstall, and…
using-game-studio-skills
Use when starting any GameStudio-CodexKIT task or when a model runner is unavailable and someone requests a confidence-based PASS.
skill-authoring-and-audit
Use when creating or revising a GameStudio-CodexKIT skill, resolving ambiguous skill triggers, auditing provenance or lifecycle maturity, or deriving reusable capabilities from session history.