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 agentmods add skills/iosdevsk/html2wp-cc-plugin/html2wpnpx skills add iOSDevSK/html2wp-cc-plugin --skill html2wpgit clone --depth 1 https://github.com/iOSDevSK/html2wp-cc-pluginWhat 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 | $0.00330 | $0.34320 |
| Opus 5 | $0.00165 | $0.17160 |
| Sonnet 5 | $0.00066 | $0.06864 |
| Haiku 4.5 | $0.00033 | $0.03432 |
Grade B, and why
html2wp scanned grade B with 2 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 2d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
friction with no safety behind it. On Linux it needs `sudo systemctl`, so it Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
suggests a build step, a curl, an install or a "cleanup script" is The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
56 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/MANIFEST.md 22 KB
- assets/scripts/allowance.sh 1.7 KB runs code
- assets/scripts/analyze-input.mjs 38 KB runs code
- assets/scripts/audit-woo-coverage.py 20 KB runs code
- assets/scripts/capture-chrome.py 11 KB runs code
- assets/scripts/capture-commerce-specimen.py 13 KB runs code
- assets/scripts/check-prereqs.sh 7.9 KB runs code
- assets/scripts/chrome-groups.mjs 29 KB runs code
- assets/scripts/cleanup.sh 8.1 KB runs code
- assets/scripts/compare-pages.py 12 KB runs code
- assets/scripts/convert-remote.sh 32 KB runs code
- assets/scripts/detect-collections.py 10 KB runs code
- assets/scripts/html-to-astro.mjs 29 KB runs code
- assets/scripts/lib/collection_coverage.py 2.5 KB runs code
- assets/scripts/lib/collection-detect.js 17 KB runs code
- assets/scripts/lib/collection-stamp.mjs 7.4 KB runs code
- assets/scripts/lib/nav-stamp.mjs 7.7 KB runs code
- assets/scripts/lib/net_guard.py 7.5 KB runs code
- assets/scripts/lib/page-equivalence.mjs 6.0 KB runs code
- assets/scripts/lib/page-key.mjs 2.8 KB runs code
- assets/scripts/lib/region-scope.js 2.6 KB runs code
- assets/scripts/lib/safe-path.mjs 5.2 KB runs code
- assets/scripts/lib/sandbox.py 11 KB runs code
- assets/scripts/lib/secret-filter.mjs 9.8 KB runs code
- assets/scripts/lib/source-lead.mjs 4.2 KB runs code
- assets/scripts/lib/web_assets.py 4.0 KB runs code
- assets/scripts/make-screenshot.py 7.7 KB runs code
- assets/scripts/make-zip.sh 19 KB runs code
- assets/scripts/materialize-js-text.py 19 KB runs code
- assets/scripts/mirror-live.py 55 KB runs code
- assets/scripts/normalize-form-fields.py 24 KB runs code
- assets/scripts/optimize-images.py 6.9 KB runs code
- assets/scripts/optimize-markup.py 19 KB runs code
- assets/scripts/prerender-spa.py 80 KB runs code
- assets/scripts/progress.sh 4.3 KB runs code
- assets/scripts/rebuild-theme.sh 3.2 KB runs code
- assets/scripts/send-verdicts.sh 7.7 KB runs code
- assets/scripts/smoke-editor.py 100 KB runs code
- assets/scripts/test-build-sandbox.sh 5.3 KB runs code
- assets/scripts/test-cleanup-guard.sh 2.8 KB runs code
- assets/scripts/test-env-compose.yml 2.1 KB
- assets/scripts/test-env.sh 21 KB runs code
- assets/scripts/test-payload-allowlist.py 5.7 KB runs code
- assets/scripts/test-retry-waits.sh 9.8 KB runs code
- assets/scripts/test-safe-path.mjs 3.9 KB runs code
- assets/scripts/test-safe-path.sh 999 B runs code
- assets/scripts/test-secret-payload.sh 7.3 KB runs code
- assets/scripts/test-served-assets.py 4.9 KB runs code
- assets/scripts/test-ssrf-guard.py 6.4 KB runs code
- assets/scripts/test-ssrf-guard.sh 2.8 KB runs code
- assets/scripts/test-upload-bounded.sh 7.4 KB runs code
- assets/scripts/verify-parity.mjs 18 KB runs code
- assets/scripts/verify-static.py 28 KB runs code
- assets/scripts/verify-wp.py 77 KB runs code
- assets/scripts/whats-here.sh 4.2 KB runs code
- VERSION 14 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.
- 2d ago First seen · 2,437 lines · 330 tokens per session scan B d8d2151cb816
html2wp is a skill published in the GitHub repository iOSDevSK/html2wp-cc-plugin (0 stars, last pushed 2d ago), with no licence file. It adds 330 tokens to every session and 34,320 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
wordpress-plugin-to-emdash
Port a WordPress plugin to EmDash CMS. Use this skill when asked to migrate, convert, or port a WordPress plugin, theme functionality, or custom post type to EmDash. Provides concept mapping and implementation patterns.
emdash-cli
Use the EmDash CLI to manage content, schema, media, and more. Use this skill when you need to interact with a running EmDash instance from the command line — creating content, managing collections, uploading media, generating types, or scripting CMS operations.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
investigate
Investigate a single EmDash issue end to end -- classify, choose a repro path, reproduce, diagnose, verify, and (only on an explicit maintainer fix directive) fix and confirm. Every verdict carries its evidence.
fix
Implement diagnose's proposed fix when verify says bug, the cause is pinned, and a maintainer triggered a fix. Follow EmDash conventions, run focused checks, publish the candidate, and report the results accurately.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.