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/paretofilm/superpowers-gstack/htmlifynpx skills add Paretofilm/superpowers-gstack --skill htmlifygit clone --depth 1 https://github.com/Paretofilm/superpowers-gstackWrote 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/paretofilm/superpowers-gstack/htmlify)<a href="https://agentmods.dev/skills/paretofilm/superpowers-gstack/htmlify"><img src="https://agentmods.dev/badge/skills/paretofilm/superpowers-gstack/htmlify.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.02538 |
| Opus 5 | $0.00026 | $0.01269 |
| Sonnet 5 | $0.00010 | $0.00508 |
| Haiku 4.5 | $0.00005 | $0.00254 |
Grade A, and why
htmlify 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 4d 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.
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
43 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.
- .gitignore 39 B
- bin/htmlify 656 B
- bun.lock 14 KB
- package.json 457 B
- src/classifyArtifact.ts 3.1 KB runs code
- src/cli.ts 7.5 KB runs code
- src/helpers/exit-codes.ts 368 B runs code
- src/helpers/levenshtein.ts 1.0 KB runs code
- src/helpers/markdown.ts 1.6 KB runs code
- src/helpers/planWiring.ts 5.4 KB runs code
- src/helpers/render.ts 4.5 KB runs code
- src/output.ts 5.1 KB runs code
- src/readArtifact.ts 1.6 KB runs code
- src/readPlan.ts 1.3 KB runs code
- src/render/components/callout-box.ts 926 B runs code
- src/render/components/comparison-matrix.ts 1.8 KB runs code
- src/render/components/diff-card.ts 989 B runs code
- src/render/components/expandable.ts 641 B runs code
- src/render/components/feedback-panel.ts 6.8 KB runs code
- src/render/components/flowchart-svg.ts 21 KB runs code
- src/render/components/index.ts 2.5 KB runs code
- src/render/components/pullquote.ts 457 B runs code
- src/render/components/stats-bar.ts 822 B runs code
- src/render/components/two-column.ts 938 B runs code
- src/render/designDoc.ts 3.4 KB runs code
- src/render/generic.ts 2.4 KB runs code
- src/render/handoff.ts 3.5 KB runs code
- src/render/plan.ts 2.9 KB runs code
- src/renderDashboard.ts 4.8 KB runs code
- src/schemas.ts 5.8 KB runs code
- styles/companion.css 37 KB
- tests/classify.test.ts 4.9 KB runs code
- tests/components.test.ts 11 KB runs code
- tests/dashboard.test.ts 3.8 KB runs code
- tests/feedback-panel.test.ts 4.7 KB runs code
- tests/flowchart-readability.test.ts 3.2 KB runs code
- tests/helpers.test.ts 5.9 KB runs code
- tests/output.test.ts 4.1 KB runs code
- tests/plan-wiring.test.ts 5.7 KB runs code
- tests/plan.test.ts 5.0 KB runs code
- tests/render.test.ts 7.4 KB runs code
- tests/silent-drops.test.ts 3.4 KB runs code
- tsconfig.json 363 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.
- 4d ago First seen · 217 lines · 51 tokens per session scan A dc953a1557b5
htmlify is a skill published in the GitHub repository Paretofilm/superpowers-gstack (2 stars, last pushed yesterday), with no licence file. It adds 51 tokens to every session and 2,538 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
brendan
Invoke when a system is slow, saturated, regressed, or near capacity and you are tempted to guess the bottleneck or reach for a random tool — Brendan Gregg's systems-performance methodology. Covers the USE method (check utilization, saturation, errors for EVERY resource), the 60-second triage checklist, TSA /…
sherlock
Invoke when a bug resists the obvious explanation and you're stuck — a "this is impossible / can't be happening" heisenbug, an intermittent or nondeterministic failure with many candidate causes, a regression with many possible culprits, a works-here-fails-there environment bug, or the moment you think "I've checked…
jamie
Invoke when you have a bug report or issue and need to confirm it's REAL before anyone fixes it — turn the report into a precise claim, faithfully recreate the reporter's conditions (the version they hit, config, data, platform, timing), build a minimal reliable reproduction, quantify how often it fires, and return a…
ronald
Invoke when comparing models or prompts and you want evidence, not a vibe check — choosing a model for a task (opus vs sonnet vs haiku; Claude vs Codex vs Gemini), A/B testing prompt variants, running a model/prompt bake-off or eval, or confirming a prompt change actually helped rather than got lucky. Runs a…
terry
Invoke when orchestrating a FLEET of parallel long-running agent tasks via a priority-queue manager over git worktrees, OR when you want a producer-consumer task queue for agents that caps concurrency to avoid OOM and pace token spend on a budget — agent queue + task list + dispatched agents + a self-pacing heartbeat…
andrej
Invoke when iterating toward a fix/optimization/answer against a live system and tempted to guess from sparse signals — an observe→analyze→act loop over instrumentation + a scalar metric + one-variable bounded experiments + a keep-or-revert gate + an append-only ledger; covers instrument-before-you-hypothesize, the…