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/proposenpx skills add skyloevil/codex-sdd --skill proposegit 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 | $0.00032 | $0.00771 |
| Opus 5 | $0.00016 | $0.00385 |
| Sonnet 5 | $0.00006 | $0.00154 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
codex-sdd:propose 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 2d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenSpec Propose
Context
Propose is the first phase of the OpenSpec workflow. It transforms a raw requirement
into a structured proposal.md that defines scope, constraints, and acceptance criteria.
This is the "constrain the requirement" step.
Trigger
Any of these patterns triggers this skill:
- User says "openspec propose" or "openspec:propose"
- User describes a new feature or change they want to make
- User says "start a new change" or "new proposal"
openspec_get_statusshows phase isidleand user describes work
Workflow
Step 1: Understand the Requirement
Ask clarifying questions if the requirement is vague:
- What is the business goal?
- What is in scope / out of scope?
- Are there any constraints or acceptance criteria?
Use minimal clarification for straightforward requests. For ambiguous/complex requests, spend more time to nail scope before writing.
Step 2: Detect Existing Layout
Call the openspec_detect_layout tool to check if an OpenSpec structure already exists
in the project. If one does, note the existing archives and specs as prior context.
Step 3: Build Context
Call docs_build_context with the requirement keywords before creating the proposal.
Also call knowledge_search for the same keywords to find prior pitfalls, decisions,
and compatibility notes. Use cited source paths from the context pack in the proposal
background or acceptance criteria when they affect scope.
Step 4: Create Proposal
Call the openspec_create_change tool with the requirement description:
openspec_create_change({
description: "<clear description of the requirement>",
background: "<optional context>",
outOfScope: "<optional out-of-scope items>",
preset: "full"
})
This generates openspec/changes/<changeId>/proposal.md plus the preset artifacts
and sets up the v2 state machine.
Step 5: Present for Review
Present the generated proposal to the user. Highlight:
- Change ID: So they can reference it later
- Scope: What will and won't be done
- Next Action: The state machine says what happens next
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.
- 2d ago First seen · 84 lines · 32 tokens per session scan A 8be022964b0d
codex-sdd:propose is a skill published in the GitHub repository skyloevil/codex-sdd (1 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 771 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.
evidence-first-debugging
Use when debugging a crash, lỗi, failing game, tool, build, service, script, or reproducible local code failure requires repro or reproduction, giả thuyết or ranked hypotheses, instrumentation, root-cause isolation, a minimal fix, regression proof, and a regression test.