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 TheGoat395/Codex-Skills --skill web-reference-researchgit clone --depth 1 https://github.com/TheGoat395/Codex-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/thegoat395/codex-skills/web-reference-research)<a href="https://agentmods.dev/skills/thegoat395/codex-skills/web-reference-research"><img src="https://agentmods.dev/badge/skills/thegoat395/codex-skills/web-reference-research/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/thegoat395/codex-skills/web-reference-research"><img src="https://agentmods.dev/badge/skills/thegoat395/codex-skills/web-reference-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00014 | $0.00341 |
| Opus 5 | $0.00007 | $0.00170 |
| Sonnet 5 | $0.00003 | $0.00068 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
web-reference-research 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 today.
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
Web Reference Research
Purpose
Convert taste references into concrete, verifiable design decisions.
Scoped execution
Apply the shared web contract once when execution crosses phases; reuse it if already read. Load only the specialist guidance relevant to the requested surface and deliverable.
Detailed Guide
Read web reference research guide for the selected workflow. Apply only the requested surface; review-only work reports findings, while authorized changes continue through implementation and relevant verification.
For item-level motion references, also read references/reconstruction-manifest.md and validate the research record with python3 "<skill-root>/scripts/verify-reference-record.py" <record.json>.
Scope and evidence
Resolve source fidelity mode before extraction. Exact authorized/supplied-source work preserves requested details; original work needs an originality delta. Motion-specific phase extraction belongs to $reference-motion-reconstruction. Empty unavailable-evidence is legitimate when nothing is missing.
For helper-driven evidence, use the typed record schema. The helper validates structure only; use actual inspection/test results for claims.
Resolve <skill-root> to this skill folder's actual absolute location; preserve project-local module resolution for Node capture tools.
Optional specialists
reference-motion-reconstruction is optional. Without it, use the bundled reconstruction-manifest guide to record observed phases, trigger, timing, responsive/reduced-motion behavior and missing evidence; do not invent unseen motion.
What ships with it
5 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.
- today Changed · -4 lines 89df02a62aea
- 5d ago Changed · +10 lines · -56 tokens per session 6f319a7d1853
- 8d ago First seen · 27 lines · 70 tokens per session scan A df8938fdd032
web-reference-research is a skill published in the GitHub repository TheGoat395/Codex-Skills (122 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 341 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 2026-09-03.
Other skills, from other repositories
design-pipeline
A build-and-test workflow for turning Figma designs into shadcn/ui components, a reusable set of interface components for React-based projects. It checks the result in a real browser at three screen sizes and runs accessibility checks.
web-typography
Expert front-end web typography — apply this whenever you are styling text on the web or making type decisions in HTML/CSS/JSX/Tailwind. Use it to choose and pair fonts, build a type scale, set body copy and headings, tune fluid/responsive type with clamp(), fix line-height, rhythm, measure and heading wraps, improve…
motion-foundations
Motion tokens, spring presets, performance rules, device adaptation, accessibility enforcement, and SSR safety for React / Next.js using motion/react. Foundation layer — all other motion skills depend on this.
motion-guide
Use when designing, adding, changing, suggesting, or reviewing UI motion. Motion Guide is a default-trigger motion decision advisor for AI coding agents: it decides whether motion should exist, selects an appropriate functional or expressive pattern, and constrains implementation with timing, easing, accessibility…
baseline-ui
Skill "baseline-ui" from humanerd-drew/opencode-drewgent, covering baseline ui, when to apply, rule categories by priority, 1. stack defaults and 2. html semantics.
conversion-accessibility-polish
Improve an existing website or web app's decision clarity, trust, forms, UX copy, and accessibility without dark patterns. Use when an agent must polish CTAs, navigation, pricing, onboarding, empty or error states, keyboard behavior, semantic HTML, focus, contrast, or the end-to-end conversion path.