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 revenantworks/claude-skills --skill revenantworks-foundation-skillwrightgit clone --depth 1 https://github.com/revenantworks/claude-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/revenantworks/claude-skills/revenantworks-foundation-skillwright)<a href="https://agentmods.dev/skills/revenantworks/claude-skills/revenantworks-foundation-skillwright"><img src="https://agentmods.dev/badge/skills/revenantworks/claude-skills/revenantworks-foundation-skillwright/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/revenantworks/claude-skills/revenantworks-foundation-skillwright"><img src="https://agentmods.dev/badge/skills/revenantworks/claude-skills/revenantworks-foundation-skillwright.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 | $0.00227 | $0.08407 |
| Opus 5 | $0.00113 | $0.04203 |
| Sonnet 5 | $0.00045 | $0.01681 |
| Haiku 4.5 | $0.00023 | $0.00841 |
Grade A, and why
revenantworks-foundation-skillwright 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 today.
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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
revenantworks-foundation-skillwright
history in CHANGELOG.md · sources in SOURCES.md · MIT (LICENSE)
Turn a one-line intent into a shipped, install-ready Agent Skill — or port an existing set to a new owner or purpose. Built from scratch, a skill is researched against current best practices, checked for a real niche, tested, and packaged. Or point it at an existing skill and get the same standards applied as an audit. Builds spec-clean neutral — a member is labeled with its pack's structural identity (name segments + frontmatter token) but carries no applied styling. Brand and voice are added only by invoking brandwright.
Build workflow: Intent → Pack & profile → Research → Niche verdict → Design catalog (one gate) → Build → Self-audit → Package
Ships no executable code of its own. Uses web search for research and baseline verification, and the surface's native file tools for delivery; where file tools are absent, every deliverable degrades gracefully to in-chat file content the user can save. Packaging optionally reaches for a shell (zip) and a stdlib-only python3 for the archive build and the exact-count hard-check (Packaging steps 3–4); both skip cleanly where no shell exists, and neither is ever required to complete a build. The universal rule it builds by: no undeclared dependencies — any tool, script, or sibling skill a built skill needs is named in its frontmatter and docs.
Turn shape
- One catalog, one gate, no drip-feed. Every decision set (design catalog, audit findings) is presented complete, once, with per-item recommendations. One approval round follows; "apply all" / "just build it" given anywhere in the request skips the gate. Never re-open a settled catalog with unsolicited additions.
- Gates render by the tool-list test. Before writing a gate or option set, scan the available tools: if any tool presents tappable options or questions to the user, use it — the plain-text fallback line (
Approve: apply all · pick IDs · adjust) is only for surfaces whose tool list has no such tool. Describing the tappable form without checking the tool list is how fallback-in-chat failures happen. - The deliverable is files, not prose. A completed build or approved audit rewrite ends with the packaged skill handed back, per Packaging below — never only a description of what would be built.
What ships with it
17 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.
- CHANGELOG.md 27 KB
- evals/RESULTS.md 98 KB
- evals/test-cases.md 45 KB
- evals/trigger-evals.md 19 KB
- LICENSE 1.0 KB
- README.md 7.9 KB
- references/build-templates.md 9.6 KB
- references/description-crafting.md 3.5 KB
- references/eval-authoring.md 2.3 KB
- references/pack-design.md 5.3 KB
- references/pack-integration.md 4.7 KB
- references/pack-registry.md 48 KB
- references/pack.md 25 KB
- references/release-doctrine.md 16 KB
- references/rubrics.md 18 KB
- references/upkeep-doctrine.md 5.5 KB
- SOURCES.md 7.0 KB
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.
- today Changed · +3 lines 95a3c8999d36
- yesterday Changed 3c5a6044b39a
- 2d ago Changed 35f2446c6d2e
- 12d ago First seen · 181 lines · 227 tokens per session scan A eff05c66de9d
revenantworks-foundation-skillwright is a skill published in the GitHub repository revenantworks/claude-skills (3 stars, last pushed today), licensed MIT. It adds 227 tokens to every session and 8,407 once invoked, about $0.0011 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
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
consult-startup
A step-by-step startup planning aid covering an idea, its market, business model, investor presentation, finances, and execution plan.
cs-channel-message
A channel-message writing tool for search ads, advertising, customer relationship messages, and app notifications. It uses the NCM sequence—Need, Channel, Moment, Message, and CTA—to adapt wording to where and when customers see it.
design-tokens-transformer
A converter for design tokens, which are named values for colors, fonts, spacing, borders, shadows, and motion. It translates one shared token source into CSS variables and Tailwind or shadcn-style theme files, and can convert them back for checking.