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/zts0hg/codexspec/codexspec-quicknpx skills add Zts0hg/codexspec --skill codexspec-quickgit clone --depth 1 https://github.com/Zts0hg/codexspecWhat 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 | $0.00023 | $0.00539 |
| Opus 5 | $0.00012 | $0.00269 |
| Sonnet 5 | $0.00005 | $0.00108 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
codexspec:quick 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick Implementation
Language Preference
Read .codexspec/config.yml. Two independent language controls apply (each falls back to language.output, then English):
- Interaction language (
language.interaction): language for all conversation with the user — questions, explanations, status messages, andcodexspecCLI terminal output. - Document language (
language.document): language for generated artifact files (requirements/spec/plan/tasks).
Converse in the interaction language and author artifacts in the document language. Apply the project's translation standard to both: translate by meaning (not word-for-word), keep English for terms with no good native equivalent, and write as if originally in that language.
User Input
the text after the $codexspec:quick skill mention
Scope Check
Quick is intended for a small, well-bounded change. Assess likely files, module span, new dependencies, and unresolved product decisions.
If the change is broad or has multiple independent outcomes, explain why the standard flow is safer and ask whether to continue with Quick.
Compact Requirement Confirmation
Even in Quick mode, do not rely on session-only context.
- Resolve only ambiguities that materially change implementation.
- Create a feature workspace and
requirements.mdusing the same timestamp feature convention as$codexspec:specify. - Present a concise confirmed requirement summary containing:
NEED-*- relevant
CON-*andDEC-* OUT-*- unresolved
OPEN-*
- Ask the user to confirm the summary.
- Persist only confirmed entries, with short User Evidence and a Confirmation Log.
Do not start generation before confirmation. If a critical question remains open, stop.
Automated Flow
Use the created feature directory explicitly for every command:
$codexspec:generate-spec <feature-dir>/requirements.md$codexspec:spec-to-plan <feature-dir>/spec.md$codexspec:plan-to-tasks <feature-dir>/plan.md$codexspec:implement-tasks <feature-dir>/tasks.md
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 · 59 lines · 23 tokens per session scan A 7bf2ab86376d
codexspec:quick is a skill published in the GitHub repository Zts0hg/codexspec (5 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 539 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
comet-bilingual-docs
在保留已确认语义、仓库结构、子模块边界和聚焦验证的前提下，同步 Comet 中英文文档、README、Skill、发布说明和网站页面。文档变更需要保持双语，或中文措辞需要英文对应版本时使用。.
intlayer-content
Define rich content structures using Intlayer content nodes. Use when the user asks to "create translations", "handle pluralization", "use markdown in content", or implement "conditional content".
intlayer-angular
Integrates Intlayer internationalization with Angular applications. Use when the user asks to "setup Angular i18n", create a new translated component, use the "useIntlayer" composable, or configure providers.
intlayer-next-js
Integrates Intlayer internationalization with Next.js App Router and Pages Router. Use when the user asks to "setup Next.js i18n", use "useIntlayer" in Server Components, or handle client-side translations in Next.js.
intlayer-react
Integrates Intlayer internationalization with React component. Use when the user asks to "setup React i18n", create a new translated component, use the "useIntlayer" hook, or configure providers.
intlayer-cli
Manages Intlayer dictionaries and configuration via the Command Line Interface. Use when the user asks to "audit translations", "build dictionaries", "sync content", or run "intlayer" commands.