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-lorewrightgit 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-lorewright)<a href="https://agentmods.dev/skills/revenantworks/claude-skills/revenantworks-foundation-lorewright"><img src="https://agentmods.dev/badge/skills/revenantworks/claude-skills/revenantworks-foundation-lorewright/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-lorewright"><img src="https://agentmods.dev/badge/skills/revenantworks/claude-skills/revenantworks-foundation-lorewright.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 | $0.00171 | $0.03119 |
| Opus 5 | $0.00086 | $0.01559 |
| Sonnet 5 | $0.00034 | $0.00624 |
| Haiku 4.5 | $0.00017 | $0.00312 |
Grade A, and why
revenantworks-foundation-lorewright 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
revenantworks-foundation-lorewright
history in CHANGELOG.md · sources in SOURCES.md · MIT (LICENSE)
Research that ends in something usable: a verdict — one direct recommendation with its evidence graded — or a playbook — a versioned reference doc that answers before it explains. Never a wall of findings.
Workflow: Intake → Criteria (verdict) / Template (playbook) → Live verification → Product → Handback
Turn shape
-
Answer up front. A verdict opens with the recommendation; a playbook opens with the answer its reader came for. Method, sources, and caveats follow — never precede.
-
Every claim wears its tag. Four grades, inline: [documented] — a fact its source sets or governs, or one it measures without a stake in it, read live there this run · [vendor-reported] — the seller's own measurement or judgement about itself · [estimate] — reasoned from tagged facts, math shown · [unverified] — found but not confirmed. An untagged claim is a defect. These four glosses are the legend and their single home — no other file in this skill restates them, it points here; where a product carries a legend for its reader, it carries them verbatim.
Vendor page, two grades — the kind of fact decides, not the publisher. Most cells are read live off the seller's own site, where "primary source" and "the seller says so" both fire. Ask what kind of fact it is. A term the vendor sets and is bound by — list price, plan limit or quota, license term, supported platform, region, release or end-of-life date, published version number — is [documented] when read live from the vendor this run: that page is the authority for it, and any other page can only copy it. A figure the vendor measured or judged about its own product — battery life, throughput, uptime, accuracy, "fastest/best", any number the seller's own testing produced — is [vendor-reported] however primary the page, because an independent measurement could return something else. Arguably both, or you cannot tell: take the weaker tag. Strength runs [documented] > [vendor-reported] > [unverified], and an [estimate] is never stronger than its weakest input.
-
One gate at most. Verdicts gate only on genuinely ambiguous criteria (one batch — the Selection must-have question rides in it too, never a second round); playbooks gate on the template once. Tool-list test governs the form.
What ships with it
10 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.
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 · +4 lines d7cc8c8107f1
- yesterday Changed 8274aaf6fd78
- 3d ago Changed · +2 lines 232b2c233df3
- 12d ago First seen · 84 lines · 171 tokens per session scan A 93f591d1c7f2
revenantworks-foundation-lorewright is a skill published in the GitHub repository revenantworks/claude-skills (3 stars, last pushed today), licensed MIT. It adds 171 tokens to every session and 3,119 once invoked, about $0.0009 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.