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 standardsgit 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/standards)<a href="https://agentmods.dev/skills/dayfinggg/openai-codex-agent-skills/standards"><img src="https://agentmods.dev/badge/skills/dayfinggg/openai-codex-agent-skills/standards/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/standards"><img src="https://agentmods.dev/badge/skills/dayfinggg/openai-codex-agent-skills/standards.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 | $0.00044 | $0.01465 |
| Opus 5 | $0.00022 | $0.00732 |
| Sonnet 5 | $0.00009 | $0.00293 |
| Haiku 4.5 | $0.00004 | $0.00146 |
Grade A, and why
standards 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 3d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standards
Follow the governing instructions and the user's requirements for communication, code style, authorization, and delegation. This skill supplies task-specific guidance, not permission to expand the task. Its workflow and output fields describe internal checks and relevant content, not a mandatory response layout or a progress report. When used within broader authorized work, continue that work through completion rather than stopping to deliver this skill's intermediate result.
Improve code clarity, correctness, maintainability, and scalability without expanding the requested scope or adding speculative architecture.
Precedence
Apply standards in this order:
- Governing system and developer instructions, followed by the user's explicit requirements.
- Applicable repository instructions that do not conflict with those requirements.
- Checked-in formatter, linter, compiler, analyzer, test, and build configuration.
- Existing local conventions that are consistent and intentional.
- Current official guidance for the installed language, framework, and database versions.
- The references in this skill.
Do not restyle a repository to match a personal preference. Resolve routine differences within the authorized scope. Ask only when an essential requirement cannot be reconciled. Treat references as conditional guidance, not permission to change project policy, upgrade dependencies, publish code, or alter live systems.
Load focused guidance
Each technology has its own directory under references/. Open that directory's index.md first, then load only the linked topic files needed for the current decision. Do not load every topic file for a technology by default. Check installed versions and target environments before applying a version-sensitive claim. Verify uncertain or changing behavior in the corresponding official documentation. A bundled reference is not proof that a feature is available in the project.
Inspect the files and project manifests before choosing references. Use references/principles/index.md only when deciding abstractions, duplication, file boundaries, refactoring, or structural tradeoffs. Use references/testing/index.md when test design, test doubles, suite reliability, or test boundaries materially affect the work. Use references/ux/index.md when the task includes interaction design, usability, user research, prototyping, or mobile interaction decisions. Then load only the language, framework, and database indexes needed for the current task.
What ships with it
60 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/openai.yaml 243 B
- references/actix/abstraction-discipline.md 702 B
- references/actix/application-factory-and-state.md 913 B
- references/actix/database-boundary.md 789 B
- references/actix/error-handling.md 825 B
- references/actix/handlers-and-extractors.md 1.1 KB
- references/actix/index.md 869 B
- references/actix/middleware-and-ordering.md 1.1 KB
- references/actix/observability.md 907 B
- references/actix/runtime-and-concurrency.md 1.2 KB
- references/actix/security.md 1.0 KB
- references/actix/sources.md 2.5 KB
- references/actix/testing-and-shutdown.md 1.0 KB
- references/algorithms/choose-by-required-operations.md 1.4 KB
- references/algorithms/complexity-and-scale.md 1.3 KB
- references/algorithms/correctness-and-boundary-cases.md 1.0 KB
- references/algorithms/index.md 533 B
- references/algorithms/measurement-and-optimization.md 779 B
- references/algorithms/sources.md 678 B
- references/angular/accessibility.md 958 B
- references/angular/architecture.md 1.5 KB
- references/angular/dependency-injection.md 1.2 KB
- references/angular/file-organization.md 759 B
- references/angular/index.md 766 B
- references/angular/migration-safe-simplicity.md 1.3 KB
- references/angular/performance-and-rendering.md 1.3 KB
- references/angular/signals-and-rxjs.md 1.8 KB
- references/angular/sources.md 3.5 KB
- references/angular/standalone-composition-and-loading.md 1.1 KB
- references/angular/state-boundaries.md 816 B
- references/angular/templates.md 1.5 KB
- references/angular/testing.md 1006 B
- references/axum/application-shape-and-state.md 882 B
- references/axum/async-and-concurrency.md 1.1 KB
- references/axum/database-boundary.md 823 B
- references/axum/errors.md 874 B
- references/axum/extractors-and-handlers.md 1.1 KB
- references/axum/index.md 862 B
- references/axum/observability.md 871 B
- references/axum/routing-and-middleware.md 1.5 KB
- references/axum/security.md 1.0 KB
- references/axum/sources.md 3.3 KB
- references/axum/testing-and-shutdown.md 1.1 KB
- references/chi/handlers-errors-and-context.md 867 B
- references/chi/index.md 648 B
- references/chi/middleware-order.md 1.1 KB
- references/chi/router-assembly.md 1.0 KB
- references/chi/security-and-operations.md 676 B
- references/chi/sources.md 474 B
- references/chi/testing-and-complexity-control.md 743 B
- references/chi/when-chi-is-justified.md 569 B
- references/csharp/analyzers-formatters-and-ci.md 1.0 KB
- references/csharp/asynchronous-code.md 1.6 KB
- references/csharp/exceptions-and-failure-contracts.md 1.3 KB
- references/csharp/immutability-records-and-collections.md 1.1 KB
- references/csharp/index.md 1.1 KB
- references/csharp/nullable-reference-types.md 952 B
- references/csharp/project-layout-and-build-files.md 987 B
- references/csharp/public-api-design.md 1.3 KB
- references/csharp/quality-baseline.md 552 B
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.
- 3d ago Changed · +3 lines · -37 tokens per session d698fe4e1bf6
- 5d ago Changed · +12 lines · +11 tokens per session 882ff1f6f109
- 10d ago First seen · 91 lines · 70 tokens per session scan A 128dcb0069a8
standards is a skill published in the GitHub repository dayfinggg/openai-codex-agent-skills (4 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 1,465 once invoked, about $0.0002 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
web-design-reviewer
This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like "review website design", "check the UI", "fix the layout", "find design problems". Detects issues with responsive design, accessibility, visual consistency, and layout breakage…
ui-reviewer
UI/UX review — accessibility, semantic HTML, z-index, animations, responsive, design tokens.
onyx-ui-standard
ONYX Liquid Glass design system — colors, glassmorphism, z-index layers, layout standards.
tg-miniapp
A collection of patterns for Telegram Mini Apps, which are web apps opened inside Telegram, including device safe areas, fixed elements, navigation buttons, sharing, and fullscreen behavior.
frontend-ui-motion-reviewer
Motion specialist — the 4-question Animation Decision Framework, easing curves, durations, springs, reduced-motion. Output in | Before | After | Why | markdown table.
threejs-color-management
Three.js color pipeline — sRGB vs Linear, toneMapping (None/ACES/Reinhard), texture colorSpace, when to use NoToneMapping for UI textures. Activate when color issues arise with 3D textures or rendered colors look wrong.