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 skills add sparklingneuronics/sparkling-skills --skill codexgit clone --depth 1 https://github.com/sparklingneuronics/sparkling-skillsWrote 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/sparklingneuronics/sparkling-skills/codex)<a href="https://agentmods.dev/skills/sparklingneuronics/sparkling-skills/codex"><img src="https://agentmods.dev/badge/skills/sparklingneuronics/sparkling-skills/codex/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/sparklingneuronics/sparkling-skills/codex"><img src="https://agentmods.dev/badge/skills/sparklingneuronics/sparkling-skills/codex.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00249 | $0.06314 |
| Opus 5 | $0.00125 | $0.03157 |
| Sonnet 5 | $0.00050 | $0.01263 |
| Haiku 4.5 | $0.00025 | $0.00631 |
Grade A, and why
codex 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex
Delegate a prompt to OpenAI's codex CLI and stream the result back. The user keeps Claude Code open while a separate model handles the side task.
When to use
Trigger on:
/codex <prompt>— explicit invocation- "ask codex ...", "run codex ...", "have codex ...", "get codex's take on ..."
- "check with codex", "validate with codex", "see what codex thinks" — generic delegation; you infer the topic (the user won't name it)
- second opinions / parallel checks on anything — code, but also non-coding: "have codex review this email", "see what codex thinks of this plan"
- "diff this with codex", "second opinion from codex"
/codex resume, "codex resume", "continue with codex" — resume the matching codex thread (see Topic-aware sessions)/codex reviewor "have codex review" — code review against the current repo (usescodex review)- "use codex to create an image / illustration of X", "have codex illustrate this" — image generation, only when codex is named (see Image generation)
- "after each step, validate with codex" — only when the user explicitly asks; run the delegation loop each step (not a standing default)
Do NOT trigger for:
- Anything where the user wants Claude Code itself to do the work ("you write it", "don't delegate this")
- delegation aimed only at agy / antigravity / gemini (
/agy,/gemini— "ask agy ...", "ask gemini ...") — those route to theagyskill. A request naming both codex and agy/gemini triggers both skills; handle the codex portion here. - A bare image request that doesn't name codex ("illustrate this", "create an image") — image generation is ambiguous across tools (other tools do it too), so the user picks by naming the tool. Explicit "use codex to …" does trigger (see Image generation).
- The homonyms / questions about codex — "the Codex Justinianus", "an illuminated codex (manuscript)", "set up Codex billing", "how does the codex CLI work" — a noun, or a question about codex, not a delegation to it.
What ships with it
7 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.
- yesterday Changed · +12 lines e0f52b96be2d
- 10d ago First seen · 228 lines · 249 tokens per session scan A 12ba9427d098
codex is a skill published in the GitHub repository sparklingneuronics/sparkling-skills (6 stars, last pushed yesterday), licensed MIT. It adds 249 tokens to every session and 6,314 once invoked, about $0.0012 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
improve-code-quality
Guided journey from a working-but-untested vibe-coded prototype to a production-ready product with tests, clean structure, a business-rules boundary, and resilience at scale. Orchestrates nine skills phase by phase - working-with-legacy-code, clean-code, refactoring-patterns, software-design-philosophy…
refactoring-patterns
Apply named refactoring transformations to improve code structure without changing behavior. Use when the user mentions "refactor this", "code smells", "extract method", "replace conditional", "technical debt", "move method", "inline variable", "decompose conditional", or "clean up this messy code". Also trigger when…
team-review
Review changed code for reuse, quality, and efficiency using a team of persistent named reviewers. This skill should be used when the user says "team review", "review with team", or wants parallel code review with persistent team members for follow-up questions. Similar to /subagent-review but reviewers persist after…
roslyn-query
Query .NET/C# codebases using Roslyn AST analysis via dotnet run file. Use for tracing data flow, auditing API usage, finding pattern violations, or ad-hoc codebase queries.
reviewer
Get a second-opinion review from Google's Antigravity CLI (agy staffer, fast Gemini) - of code (a diff, PR, working tree) or of a decision, plan, or design. Use when the user says /agy:reviewer, "have agy review this", "second opinion on my diff/PR/plan", or after finishing work and wanting an independent verifier…
review-responder
Use when receiving feedback on code you implemented, responding to reviewer comments, deciding which review suggestions to implement, or pushing back on incorrect review feedback.