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/yankieldbc2/codex-skills-library/skill-authoringnpx skills add YankielDBC2/codex-skills-library --skill skill-authoringgit clone --depth 1 https://github.com/YankielDBC2/codex-skills-libraryWrote 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/yankieldbc2/codex-skills-library/skill-authoring)<a href="https://agentmods.dev/skills/yankieldbc2/codex-skills-library/skill-authoring"><img src="https://agentmods.dev/badge/skills/yankieldbc2/codex-skills-library/skill-authoring.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 5.1 | $0.00026 | $0.00312 |
| Opus 5 | $0.00013 | $0.00156 |
| Sonnet 5 | $0.00005 | $0.00062 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
skill-authoring 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 5d 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.
What it actually says
Skill Authoring
Goal
Create high-quality skills that Codex can discover and apply reliably.
When to use
Use when adding a new skill, improving an existing skill, reviewing skill quality, creating references, or deduplicating overlapping skills.
When not to use
Do not use for normal product implementation unless the task is to update the skill library itself.
Inputs
Inspect the proposed skill purpose, existing similar skills, docs/SKILL_SPEC.md, docs/STYLE_GUIDE.md, and docs/QUALITY_RUBRIC.md.
Workflow
- Define the single job of the skill.
- Search for overlapping skills before creating a new one.
- Write precise activation frontmatter.
- Put the durable process in
SKILL.md. - Move long examples to
references/. - Add scripts only for deterministic checks.
- Run validation and duplicate checks.
- Generate the catalog after changes.
Quality bar
A good skill is narrow, discoverable, safe, testable, and easy to maintain.
Validation
Run npm run validate, npm test, and npm run catalog.
Final response
Report the skill created or changed, why it is not duplicated, validation output, and any future improvement ideas.
What ships with it
4 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.
- 5d ago First seen · 49 lines · 26 tokens per session scan A 0cd6f9d371e1
skill-authoring is a skill published in the GitHub repository YankielDBC2/codex-skills-library (10 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 312 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
antigravity-skill-orchestrator
A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.
torchforge-rl-training
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.
pentest-playbook
7-phase pentest pipeline from passive recon to exploitation.
recon-playbook
Use when starting or restructuring an authorized external web and API assessment.