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/implementnpx skills add skyloevil/codex-sdd --skill implementgit 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 | $0.00029 | $0.00806 |
| Opus 5 | $0.00015 | $0.00403 |
| Sonnet 5 | $0.00006 | $0.00161 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
codex-sdd:implement 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenSpec Implement
Context
Implement is the third phase of the OpenSpec workflow. It executes the tasks
from tasks.md one by one, tracking progress and updating the state machine.
This is the "execute with discipline" step.
Trigger
Any of these patterns triggers this skill:
- User says "openspec implement" or "openspec:implement"
- User says "start implementation" or "execute tasks"
openspec_get_statusshows phase isimplementopenspec_get_statusshows phase isplanwith design confirmed
Prerequisites
- An approved
openspec/changes/<changeId>/design.mdfor full preset changes - A generated
openspec/changes/<changeId>/tasks.mdwith tasks listed - User has confirmed readiness to implement
Workflow
Step 1: Read Tasks
Call openspec_read_artifact({ artifactId: "tasks" }) to understand the full task list and identify
incomplete tasks.
Step 2: Check Status
Call openspec_get_status to confirm the project is in the implement phase.
Step 3: Execute Next Task
Work through tasks one at a time:
- Find the first incomplete task (marked
[ ]in tasks.md) - Read
design,specs, andimplementation_notesartifacts when present - Implement the required code changes
- Run focused verification for the task
- Call
openspec_record_validation_evidencewith the check result - Call
openspec_record_iterationwith changed files, commands, test results, errors, and evidence references - After implementation is done, ask user to verify the change when the task has medium/high risk, external side effects, or ambiguous acceptance criteria
- Call
openspec_update_task({ taskId: "T1", done: true })only after passed evidence exists or the user explicitly approves pending validation - Repeat for the next incomplete task
Step 4: Validation Checkpoints
After each task, provide a brief summary:
- What was implemented
- Related files changed
- Any notable decisions or deviations from the design
Gate: Destructive Changes — Auto-pause and ask before:
- Deleting or renaming files
- Changing public API signatures
- Modifying database schemas
- Large refactors affecting existing tests
- Writing to external systems
- Security-sensitive or permission-sensitive changes
- Flag these in the summary and ask for confirmation before proceeding
with
openspec_request_human_review.
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 · 89 lines · 29 tokens per session scan A abcfa2eb57a0
codex-sdd:implement is a skill published in the GitHub repository skyloevil/codex-sdd (1 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 806 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 2026-08-31.
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.