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 joohw/html2link-skill --skill html2linkgit clone --depth 1 https://github.com/joohw/html2link-skillWrote 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/joohw/html2link-skill/html2link)<a href="https://agentmods.dev/skills/joohw/html2link-skill/html2link"><img src="https://agentmods.dev/badge/skills/joohw/html2link-skill/html2link/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/joohw/html2link-skill/html2link"><img src="https://agentmods.dev/badge/skills/joohw/html2link-skill/html2link.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 | $0.00063 | $0.00918 |
| Opus 5.5 | $0.00025 | $0.00367 |
| Sonnet 5.5 | $0.00013 | $0.00184 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
html2link scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
4. Prefer the `html2link` CLI when it is installed; otherwise use the anonymous curl fallback. How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
html2link Artifact Publishing
Publish a finished local artifact and return the exact URL from the API. Treat every generated URL as public.
Core workflow
- Finish and verify the artifact before uploading it.
- Package a multi-file static site as a ZIP containing
index.html. - Check that the artifact contains no secrets, credentials, or unintended private data.
- Prefer the
html2linkCLI when it is installed; otherwise use the anonymous curl fallback. - Parse the exit status and JSON response. Do not claim success unless it contains
url. - Return the exact
urlvalue as a clickable link. Do not reconstruct it fromslug.
Publish a new artifact
With the CLI:
html2link publish /absolute/path/to/report.html
Anonymous curl fallback for files up to 1 MB:
curl --fail-with-body -F "file=@/absolute/path/to/report.html" https://html2link.dev/api/upload
For larger files, use an API token from the signed-in home page:
HTML2LINK_API_TOKEN="..." html2link publish /absolute/path/to/report.html
Keep authenticated operations in the CLI so credentials stay in the local process environment rather than being embedded in reusable shell commands.
Use --json when another program needs the complete response:
html2link publish /absolute/path/to/report.html --json
Handle a successful response
{
"slug": "a1B2c3D4",
"updateToken": "keep-this-private",
"url": "https://html2link.dev/x/a1B2c3D4",
"kind": "html",
"size": "42 KB",
"updated": false
}
- Return
urlto the user. - Keep
updateTokenprivate. Never include it in a public link or expose it unless the user explicitly needs to manage the upload. - Retain
slugwithupdateTokenonly when the user asks to update or delete the same link later.
Update an existing link
Use the original slug, its updateToken, and the replacement file. A successful update keeps the public URL unchanged.
html2link update /absolute/path/to/report.html --slug a1B2c3D4 --update-token "keep-this-private"
What ships with it
1 file 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.
- 1mo ago First seen · 102 lines · 63 tokens per session scan A 2f712d0d4440
html2link is a skill published in the GitHub repository joohw/html2link-skill (3 stars, last pushed 3mo ago), licensed MIT. It adds 63 tokens to every session and 918 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
kelly-devops
Product-fleet ops desk (Busabase App-in-Skill) for uptime/service health, SSL certificate expiry, domain renewal, API key rotation, cloud spend anomalies, and a review queue of agent-proposed action cards. Use when the user invokes $kelly-devops or /kelly-devops, or asks about uptime, service health checks, SSL…
insforge-cli
Use this skill whenever someone needs a backend, or a task touches InsForge backend or cloud infrastructure through the InsForge CLI: projects, SQL, migrations, RLS policies, functions, storage, backups, deployments, compute, secrets, config, schedules, logs, diagnostics, advisor scans and suppressions, import/export…
mirrord-prev-env
Help users create and manage mirrord preview environments — running a modified service as an isolated pod in a shared Kubernetes cluster, scoped by an environment key and HTTP/queue traffic filtering, so teams can validate and review changes against real traffic without affecting live services. Use when a developer…
cloudflare-one
Design, configure, troubleshoot, or review Cloudflare One Zero Trust and SASE deployments. Use cloudflare-one-migrations for migration planning from other vendors.
boost
Use this skill whenever the user wants to cut their RPC bill, or asks about Goldsky Boost — the free CDN that sits in front of an RPC endpoint they already pay for, serving cacheable reads from Goldsky's indexed data and forwarding everything else to their own provider unchanged. Triggers on: 'Boost', 'goldsky boost'…
mirrord-kafka
Helps DevOps engineers configure mirrord Operator's Kafka queue splitting feature end-to-end. Generates the MirrordSplitConfig and MirrordPropertyList Kubernetes CRD YAMLs (the current resources; MirrordKafkaTopicsConsumer + MirrordKafkaClientConfig are deprecated but still supported), the matching mirrord.json…