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 Postpartum-genushyacinthus29/dotnet-skills --skill dotnet-webhintgit clone --depth 1 https://github.com/Postpartum-genushyacinthus29/dotnet-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/postpartum-genushyacinthus29/dotnet-skills/dotnet-webhint)<a href="https://agentmods.dev/skills/postpartum-genushyacinthus29/dotnet-skills/dotnet-webhint"><img src="https://agentmods.dev/badge/skills/postpartum-genushyacinthus29/dotnet-skills/dotnet-webhint/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/postpartum-genushyacinthus29/dotnet-skills/dotnet-webhint"><img src="https://agentmods.dev/badge/skills/postpartum-genushyacinthus29/dotnet-skills/dotnet-webhint.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 | $0.00053 | $0.01119 |
| Opus 5.5 | $0.00021 | $0.00448 |
| Sonnet 5.5 | $0.00011 | $0.00224 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
dotnet-webhint 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 1mo 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.
This is a copy
97% identical to dotnet-webhint — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
webhint for Browser-Facing Frontends in .NET Repositories
Trigger On
- the repo ships a browser-facing site and the user asks about accessibility, performance, SEO, security headers, or page quality
- the repo has
.hintrc,hintscripts, or a served local frontend that should be audited - the team needs more than syntax linting and wants runtime-oriented site checks
Do Not Use For
- JavaScript or TypeScript semantic linting; route that to
dotnet-eslintordotnet-biome - stylesheet-only linting; route that to
dotnet-stylelint - static HTML structure checks alone; route that to
dotnet-htmlhint
Inputs
- the nearest
AGENTS.md package.json.hintrcif present- the real audit target: local dev URL, preview URL, deployed URL, or built output
Workflow
- Choose the audit surface deliberately:
- running local URL such as
https://localhost:3000 - preview or deployed URL
- local connector against built output when no browser runtime is needed
- running local URL such as
- Prefer repo-local installation and a checked-in
.hintrc. - Start from a documented preset such as
web-recommended, then customize only for real repo requirements. - Add repeatable scripts to
package.json, for example:hint https://localhost:3000hint https://example.test --config .hintrc
- Keep runtime prerequisites explicit:
- supported Node.js version
- browser availability when the connector needs Chromium-based automation
- Treat findings as categorized work:
- headers and transport
- accessibility and HTML issues
- performance
- PWA and manifest signals
- Re-run the audit after fixes on the same URL or build output so results are comparable.
Bootstrap When Missing
- Detect current state:
rg --files -g 'package.json' -g '.hintrc*'rg -n '"hint"' --glob 'package.json' .
- Prefer a repo-local install:
npm install --save-dev hint
- Create or refine
.hintrcwith a known baseline such asweb-recommended. - Add repeatable commands to
AGENTS.mdandpackage.json, then verify with:npx hint https://localhost:3000npx hint -c ./.hintrc https://example.com
- Return
status: configuredif the repo now has a working site-audit gate, orstatus: improvedif the baseline was tightened. - Return
status: not_applicablewhen the repo does not expose a stable browser-facing surface that can be audited in the current task.
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.
- 1mo ago First seen · 108 lines · 53 tokens per session scan A 2b8a0e1392d7
dotnet-webhint is a skill published in the GitHub repository Postpartum-genushyacinthus29/dotnet-skills (13 stars, last pushed 15d ago), licensed MIT. It adds 53 tokens to every session and 1,119 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to dotnet-webhint, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
llm-friendly-context
Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.
tiered-memory
Three-tier agent memory model (hot/cold/wiki) for 20-55% context reduction per spawn.
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…
a-philosophy-of-software-design
Apply John Ousterhout-inspired software design rules when reducing complexity, designing module boundaries, or reviewing APIs and abstractions.
verify-language
Language-specific verification for Python, TypeScript/JavaScript, and Go. Checks type safety, language idioms, and best practices. Use when asked to "verify language", "check types", or for language-specific checks.
verification
Full agent verification suite. Runs security, patterns, quality, and language-specific checks. Use when asked to "verify agent", "verify my agent", "audit agent", or "full verification".