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 VonTerraProject501c3/slushpile --skill redesign-templatesgit clone --depth 1 https://github.com/VonTerraProject501c3/slushpileWrote 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/vonterraproject501c3/slushpile/redesign-templates)<a href="https://agentmods.dev/skills/vonterraproject501c3/slushpile/redesign-templates"><img src="https://agentmods.dev/badge/skills/vonterraproject501c3/slushpile/redesign-templates/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/vonterraproject501c3/slushpile/redesign-templates"><img src="https://agentmods.dev/badge/skills/vonterraproject501c3/slushpile/redesign-templates.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 137 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- high Anti-Refusal · line 153 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium Excessive Agency · line 155 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00053 | $0.02625 |
| Opus 5 | $0.00026 | $0.01313 |
| Sonnet 5 | $0.00011 | $0.00525 |
| Haiku 4.5 | $0.00005 | $0.00263 |
Grade A, and why
redesign-templates 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 11d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Redesign Templates
Change how the documents look without changing what a machine reads out of them.
templates/resume.tex and templates/cover_letter.tex ship in one house style. It is a defensible style and it is not the user's. This skill produces a variant they own.
Every templates/... path in this file is relative to the plugin, not to the workspace. They are read from there and never written back to there; the variant goes in the user's own directory. Resolve them against the directory this skill file was itself loaded from — that works on every harness, where a harness-specific plugin-root variable does not.
Arguments:
$1— optional. A direction: a palette, a font family, a reference PDF or image, an adjective. With nothing, interview for it.
Announce at start: "Redesigning the resume and letter templates. The ATS rules are fixed; everything visual is open. I'll compile and check the extraction before and after."
The One Thing That Makes This Skill Dangerous
A redesign is judged by eye and graded by a parser. Those are different judges, and the second one never reports back.
A two-column layout, a sidebar of icons, a header block, a skills table: each of these looks better to a person and reads worse to an ATS, and the failure is silent. Nothing errors. The PDF looks correct. The extracted text has the dates in one column and the employers in another, and the candidate never learns that this is why nobody called.
So this skill holds a fixed set of constraints and changes everything else. The constraints are listed below, and they are not preferences.
Fixed Constraints
These do not move, whatever the user asks for. If the user asks for one of them anyway, say once what it costs and then do what they decided — it is their application. Record the override in a comment at the top of the file so the next run of this skill does not silently revert it.
- Single column for content. Multi-column layouts get read in the wrong order, and the resulting text interleaves two unrelated streams. This is the single most damaging change available in this skill.
- No tables carrying content, no text boxes, no icons carrying meaning. An icon that replaces the word "Email" removes the word "Email" from the extracted text. A phone glyph is not a phone number.
- Contact details in the body, never in
\headeror\footer. Roughly a quarter of ATS drop header and footer content entirely, and the dropped field is the one they would have called. - Standard section headings. "Work Experience", not "Where I've Been". The parser matches on the string.
- Month and year on every role. A year-only date makes tenure ambiguous, and an ambiguous tenure gets resolved against the candidate.
- Selectable text. No content rendered as an image, no font that fails to embed a usable ToUnicode map. Test this rather than assuming it; see Phase 4.
- The two documents stay a matched pair. Same palette, same fonts, same header treatment. They are the only two things in the application a screener sees side by side.
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.
- 11d ago First seen · 156 lines · 53 tokens per session scan A 675234380fba
redesign-templates is a skill published in the GitHub repository VonTerraProject501c3/slushpile (15 stars, last pushed 25d ago), licensed MIT. It adds 53 tokens to every session and 2,625 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 2026-08-30.
Other skills, from other repositories
create-diagram
Create architecture diagrams from a local codebase or system description. Use when the user asks to diagram a repo, map system architecture, show component relationships, create drill-down views, or explain a system visually with tld.
icon-composer-app-icon-workflow
Design, preview, validate, and integrate Apple app icons with Icon Composer. Use when a task mentions Icon Composer, .icon documents, Liquid Glass app icons, ictool preview exports, app icon design for iOS, iPadOS, macOS, or watchOS, or guided Icon Composer GUI work through Computer Use.
design-system-specification
Design a production-ready Design System and UI/UX visual style guide. Covers design tokens (colors, typography, spacing, shadows, radius), components (buttons, inputs, cards, tables, modals, navigation), layouts, interaction/hover states, iconography, motion design, responsive behavior, accessibility (WCAG 2.2), and…
ux-flow-specification
Document the complete user experience of a product - information architecture, user journeys, screen-by-screen flows, and every UI state (loading, empty, error, success) - independent of visual styling. Use to define exactly how a user moves through a product before or alongside implementation, so navigation and…
sf-symbols-workflow
Guide SF Symbols selection, inspection, customization, rendering modes, variable color, symbol effects, animated symbols, custom symbols, accessibility semantics, availability checks, and Apple app integration. Use when a task mentions SF Symbols, the SF Symbols app, systemImage names, symbolRenderingMode…
apple-typography-workflow
Guide Apple platform typography decisions and implementation across SwiftUI Font, UIKit UIFont, AppKit NSFont, San Francisco system fonts, SF Pro, SF Compact, SF Mono, SF Pro Rounded, New York serif design, Dynamic Type, text styles, fontDesign, fontWeight, fontWidth, monospaced digits, custom font bundle integration…