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/jcmaker/prd-maker/prd-to-htmlnpx skills add jcmaker/prd-maker --skill prd-to-htmlgit clone --depth 1 https://github.com/jcmaker/prd-makerWhat 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 | $0.00106 | $0.00798 |
| Opus 5 | $0.00053 | $0.00399 |
| Sonnet 5 | $0.00021 | $0.00160 |
| Haiku 4.5 | $0.00011 | $0.00080 |
Grade A, and why
prd-to-html 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 3d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD to HTML
Convert an existing markdown document into a single self-contained HTML page a human can actually read.
Announce at start (in the user's language): "prd-to-html 스킬로 HTML 뷰를 만들겠습니다."
What this is for
PRD.md is written for coding agents. The project owner has to understand the same document — what is being built, what is deliberately excluded, and which (가정) / (assumption) items they still need to confirm. This skill renders that view.
The converter is a deterministic script, not a judgment call. Your job is to pick the right target file, run it, and report the result accurately. Do not write HTML yourself, and do not edit the output.
Workflow
Step 1 — Pick the target
Use the file the user named. If they named none, use PRD.md in the current working directory.
If the target does not exist, say so and stop. Never invent a PRD, and never fall back to a different file without asking.
Step 2 — Run the converter
python3 <converter> <target>
The converter is ../prd-maker/scripts/prd_to_html.py, relative to this skill's own directory. In Claude Code that resolves to ${CLAUDE_PLUGIN_ROOT}/skills/prd-maker/scripts/prd_to_html.py; other agents expose it as a sibling of the folder this SKILL.md was loaded from. It needs only Python 3 — no dependencies to install.
It writes <target>.html beside the source. Pass --output <path> when the user wants it elsewhere. It prints the output path and the number of (가정) / (assumption) items it found.
Exit code 2 means a usage error — a missing file, a bad argument, or a file that is not valid UTF-8. Report what it says rather than retrying with different arguments.
Step 3 — Report
Tell the user:
- Where the HTML was written.
- The assumption count, if it is greater than zero — those are the items the owner still needs to confirm, and the HTML lists each one with its source line.
- That the HTML is a derived view: it contains nothing that is not in the markdown, and edits belong in the source file. Regenerate it after changing the markdown; never hand-edit the HTML.
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.
- 3d ago First seen · 51 lines · 106 tokens per session scan A 2619bd5de28d
prd-to-html is a skill published in the GitHub repository jcmaker/prd-maker (11 stars, last pushed 14d ago), licensed MIT. It adds 106 tokens to every session and 798 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
etsy-category-listing
Etsy category page scraper: given an Etsy category URL (e.g. https://www.etsy.com/c/jewelry) and optional page number, returns paginated product listings with listingId, shopId, title, url, image, salePrice, originalPrice, currency, rating, reviewCount, shopName, isAd, freeShipping, badge from category and subcategory…
human-approval
Request human approval before performing a SAFETY-CRITICAL, IRREVERSIBLE, or SCOPE-EXPANDING action — submit a structured context (action, scope, risk, consequence) plus options, then STOP the current turn. The platform redispatches the agent after the human decides. NEVER use for routine deliverables (writing docs /…
firebase-analytics
Use when logging analytics events, setting user properties, configuring default event parameters, building funnels, or adding screen-view tracking.
firebase-remote-config
Use when implementing feature flags, running A/B tests, setting parameter defaults, fetching/activating config, or enabling real-time config updates.
git-master
MUST USE whenever a task needs a commit or git-history investigation. Covers atomic commits, staging, commit-message style, rebase, squash, fixup/autosquash, blame, bisect, reflog, git log -S/-G, and questions like who wrote this or when was this added. Do not use for ordinary code edits unless the user asks for git…
prismer-evolve-record
Record the outcome of applying an evolution strategy. Use after resolving an error where prismer-evolve-analyze provided a recommendation, to feed back success or failure to the network.