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 Abhishek-Chougule/website-standards-auditor --skill website-standards-auditorgit clone --depth 1 https://github.com/Abhishek-Chougule/website-standards-auditorWrote 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/abhishek-chougule/website-standards-auditor/website-standards-auditor)<a href="https://agentmods.dev/skills/abhishek-chougule/website-standards-auditor/website-standards-auditor"><img src="https://agentmods.dev/badge/skills/abhishek-chougule/website-standards-auditor/website-standards-auditor/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/abhishek-chougule/website-standards-auditor/website-standards-auditor"><img src="https://agentmods.dev/badge/skills/abhishek-chougule/website-standards-auditor/website-standards-auditor.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 | $0.00182 | $0.04103 |
| Opus 5.5 | $0.00073 | $0.01641 |
| Sonnet 5.5 | $0.00036 | $0.00821 |
| Haiku 4.5 | $0.00018 | $0.00410 |
Grade A, and why
website-standards-auditor 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 2mo 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Website Standards Auditor
This skill audits a website against one fixed set of organization standards and then fixes the gaps. It works on a brand new project, a project still in development, or an already live site. It always runs in two phases with a hard approval gate between them: first it produces a written gap report (gap_identification.md), then, only after the user explicitly approves, it repairs the approved items and reconciles .gitignore and README.md.
The standards are fixed and bundled with this skill. Do not invent new rules and do not drop existing ones. The three pillars are:
- Engineering and content rules (see
references/coding_rules.md) - Mandatory git policy and the standard
.gitignore(seereferences/git_policy.mdandreferences/gitignore_standard.txt) - Website quality criteria covering SEO, GEO, AEO, structured data, performance, and more (see
references/website_criteria.md)
Operating principles (these are binding for every run)
These principles come from the organization rules and override convenience at every step.
- Never make assumptions. Detect facts from the repository, the served site, and the user's words. When a fix needs a value that cannot be derived from those sources (for example the canonical domain, the default language and locale, the legal or brand name, social profile URLs, or contact name, address, and phone), do not guess and do not insert a plausible placeholder as if it were real. List the item under "Information required from user" in the gap report and ask for it before writing anything that depends on it.
- Never use the em dash. Do not use the em dash character in anything you write or edit, including this skill's own output files (
gap_identification.md,fix_summary.md) and any site content you touch. Use a comma, colon, parentheses, or a reworded sentence instead. The audit also treats every em dash already present in the target site as a defect to be fixed. - Always keep
.gitignoreandREADME.mdup to date. Every run ends by reconciling these two files against the current state of the project, even if the user only asked for an SEO check. - Never change existing UI/UX. When fixing gaps or scaffolding new pages, preserve all existing font stacks, color tokens, spacing, border radii, shadow, and layout. New pages (privacy, 404, offline, or any other page created during a fix run) must inherit the project's existing design system. Read the project's CSS, design tokens, or component library before writing a new page. If no design system is detectable, use the bundled template defaults from
assets/and note infix_summary.mdthat the user should update the tokens. This rule applies to every file the skill touches, not only to HTML pages.
What ships with it
15 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.
- assets/gap_identification_template.md 7.2 KB
- assets/llms_txt_template.md 1.1 KB
- assets/not_found_template.html 2.1 KB
- assets/offline_page_template.html 2.2 KB
- assets/privacy_page_template.html 8.4 KB
- assets/robots_txt_template.txt 425 B
- assets/schema_templates.md 3.0 KB
- assets/terms_page_template.html 9.9 KB
- README.md 4.9 KB
- references/coding_rules.md 4.4 KB
- references/git_policy.md 2.3 KB
- references/gitignore_standard.txt 2.9 KB
- references/website_criteria.md 31 KB
- scripts/audit_site.py 59 KB runs code
- scripts/download_media.py 12 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.
- 2mo ago First seen · 150 lines · 182 tokens per session scan A 94e276b51dc8
website-standards-auditor is a skill published in the GitHub repository Abhishek-Chougule/website-standards-auditor (1 stars, last pushed 4mo ago), licensed MIT. It adds 182 tokens to every session and 4,103 once invoked, about $0.0007 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 2026-08-31.
website-standards-auditor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| website-standards-auditorAbhishek-Chougule/website-standards-auditor | Skill | 1 | 4mo ago | MIT | A | 182 | Claude Code, Codex |
| seo-auditseo-skills/seo-audit-skill | Skill | 663 | 22d ago | MIT | A | 80 | Claude Code |
| seo-auditseo-skills/seo-audit-skill | Skill | 663 | 22d ago | MIT | A | 80 | Claude Code |
| skill-routerhussi9/skill-router | Skill | 31 | 2d ago | MIT | A | 69 | Claude Code |
| daily-workingtms-tungnguyen3/daily_working | Skill | 5 | 1mo ago | MIT | A | 98 | Claude Code |
| skillmamaMagithar/SKILLmama | Skill | 8 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| Pre-Launch Website Auditbzsasson/pre-launch-audit-skill | Skill | 10 | 6mo ago | MIT | A | 92 | Claude Code |