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 dayfinggg/openai-codex-agent-skills --skill skill-creatorgit clone --depth 1 https://github.com/dayfinggg/openai-codex-agent-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/dayfinggg/openai-codex-agent-skills/skill-creator)<a href="https://agentmods.dev/skills/dayfinggg/openai-codex-agent-skills/skill-creator"><img src="https://agentmods.dev/badge/skills/dayfinggg/openai-codex-agent-skills/skill-creator/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/dayfinggg/openai-codex-agent-skills/skill-creator"><img src="https://agentmods.dev/badge/skills/dayfinggg/openai-codex-agent-skills/skill-creator.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 | $0.00033 | $0.00659 |
| Opus 5.5 | $0.00013 | $0.00264 |
| Sonnet 5.5 | $0.00007 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
skill-creator 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 12d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
This workflow comes from Claude's skill-creator and uses the tools actually available in Codex. Preserve the user's skill name and destination. A narrow edit does not need a full evaluation campaign.
Define and write
Use the conversation and existing artifacts to establish the task, trigger boundary, expected result and required tools. Ask only for missing information that changes the result. Write a concise SKILL.md with name and description in YAML frontmatter. Describe the real workflow and when it applies, without pushy catchall triggers or assumptions about model weaknesses.
Keep non-obvious decisions and essential constraints in the main file. Route detailed modes, schemas and reusable mechanics to existing references or scripts, loading them only when the task needs them. Explain why a fragile operation requires its sequence. Let Codex choose ordinary implementation details.
Preserve scope, permissions and project conventions. Do not require unrelated deliverables, automatic external actions, a fixed number of steps or permanent evaluation artifacts for a simple edit.
Evaluate when needed
Use realistic requests, including a close negative case for the description. Check observable outcomes, not whether the model repeats prescribed wording. Compare against the original skill or a no-skill baseline when that comparison answers the user's question.
Run evaluation tasks with authorized tools and side effects. Use Codex subagents only when session rules allow delegation. Give an independent evaluator the request and raw artifacts, not the desired answer or prior conclusions. When independent execution is unavailable, distinguish a local check from a benchmark.
Read agents/grader.md to grade expectations, agents/comparator.md for blind comparison and agents/analyzer.md for benchmark analysis. Read references/schemas.md only when producing the corresponding evaluation files.
What ships with it
17 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.
- agents/analyzer.md 10 KB
- agents/comparator.md 7.1 KB
- agents/grader.md 8.8 KB
- assets/eval_review.html 6.9 KB
- eval-viewer/generate_review.py 16 KB runs code
- eval-viewer/viewer.html 44 KB
- LICENSE.txt 11 KB
- references/schemas.md 12 KB
- scripts/__init__.py 0 B runs code
- scripts/aggregate_benchmark.py 14 KB runs code
- scripts/generate_report.py 13 KB runs code
- scripts/improve_description.py 11 KB runs code
- scripts/package_skill.py 4.1 KB runs code
- scripts/quick_validate.py 3.9 KB runs code
- scripts/run_eval.py 11 KB runs code
- scripts/run_loop.py 13 KB runs code
- scripts/utils.py 1.6 KB runs code
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.
- 12d ago First seen · 37 lines · 33 tokens per session scan A 0dcabda603ef
skill-creator is a skill published in the GitHub repository dayfinggg/openai-codex-agent-skills (8 stars, last pushed 11d ago), licensed MIT. It adds 33 tokens to every session and 659 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-30.
Other skills, from other repositories
stss
Reduce defensive disclaimers, stacked hedging, and self-protective narration when drafting, rewriting, or auditing proposals, articles, case studies, captions, and other reader-facing prose. Use when defensive wording is requested for review or appears in a draft, including wording the assistant adds. Preserve…
research
Performs deep research on a topic via deepresearch. Simulates a multi-step research process and returns a comprehensive research result as a string.
audit
Repo audits, one mode or all (codebase, docs, process, perf, tests, threat-model, motion, SEO, debt). Triggers "audit the codebase", "full audit", "perf audit", "audit the tests", "threat model", "motion audit", "seo audit", "debt ledger".
handoff
Save state at the end of a session, or resume from the last one. Triggers "wrapping up", "running out of context", "done for today", "continue where we left off", "resume".
review-batch
Batch-review diffs from several agents with per-change re-entry cards and abridged reading diffs. Triggers "review batch", "what's pending review", "reading diff", or after fanning out several agents.
refactor
Behavior-preserving restructuring of code outside the current diff, such as extracting modules, renaming across files, or paying down debt. Triggers "refactor X", "restructure", "extract Y from Z". Just-changed code goes to /zero-tech-debt.