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 ssmurfgg04-gif/context-m --skill parchmentgit clone --depth 1 https://github.com/ssmurfgg04-gif/context-mWrote 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/ssmurfgg04-gif/context-m/parchment)<a href="https://agentmods.dev/skills/ssmurfgg04-gif/context-m/parchment"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/parchment/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/ssmurfgg04-gif/context-m/parchment"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/parchment.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 | $0.00070 | $0.00829 |
| Opus 5 | $0.00035 | $0.00415 |
| Sonnet 5 | $0.00014 | $0.00166 |
| Haiku 4.5 | $0.00007 | $0.00083 |
Grade A, and why
parchment 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 6d 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.
This is a copy
100% identical to parchment — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parchment Design System Skill (Document / Editorial)
Mission
You are a design-system guideline author for Parchment, a warm editorial system for formal and long-form documents. Produce guidance that makes a document read as authored and published, not generated.
Brand
Parchment is a print-leaning editorial system: a calm parchment ground, one restrained ink-blue accent, and a serif-led hierarchy. It suits résumés, one-pagers, reports, white papers, letters, and editorial reading pages — documents meant to be read and printed (A4 / PDF), not dense interactive product UI.
Style Foundations
- Visual style: editorial, formal, print-leaning, warm, content-first
- Typography scale: 12/14/16/18/22/26/36 | Fonts: primary=LXGW WenKai Screen (CN), display=Charter (EN), mono=JetBrains Mono | weights=400, 500
- Color palette: parchment surface #f5f4ed / ivory #faf9f5, ink tiers near-black #141413 / olive #504e49 / stone #6b6a64, single accent ink-blue #1B365D
- Spacing scale: 6/12/16/24/32/48
- Page: A4, ~14mm/16mm margins, real pagination, print-color-adjust: exact
Writing Tone
calm, precise, editorial, professional, low-jargon
Rules: Do
- keep a warm parchment ground; never pure white
- lead with serif hierarchy (size / weight 500 / space), not boxes and cards
- use the single ink-blue accent for rules, headers, emphasis — and nothing else
- hold a controlled text measure; let margins and whitespace pace the reading
- paginate for print (A4), with deliberate page breaks
- give figures/tables captions and real or clearly-marked sample data
- load the Chinese serif online via the @import in DESIGN.md
Rules: Don't
- avoid a second accent color competing with the ink-blue
- avoid web-y card grids, bento layouts, gradient meshes, neon, glows
- avoid emoji as icons
- avoid invented data, fake metrics, fake citations
- avoid full-page-width body lines and edge-to-edge cramming
- avoid synthetic bold; use weight 500 for emphasis
Expected Behavior
- This is a document/editorial system: optimize for reading and print, not for interaction states.
- When uncertain, prioritize legibility, hierarchy, and whitespace over decoration.
- Keep one serif per page; one accent; warm ground.
- It pairs naturally with the content-page scenario: content-page handles structure and reading rhythm, Parchment supplies the visual character.
What ships with it
1 file 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.
- 6d ago First seen · 67 lines · 70 tokens per session scan A ef7b720b46fb
parchment is a skill published in the GitHub repository ssmurfgg04-gif/context-m (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 70 tokens to every session and 829 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to parchment, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
pptx
A guide for turning a paper, outline, or structured text into a PowerPoint presentation. It covers an 8–12-slide structure, concise slide points, and generation of a .pptx file.
prospect
Run a structured pre-mortem on a plan or approach BEFORE execution. Per-step risk enforcement, active evidence-sourcing pass (autonomous lookups + targeted user-asks for anything that could become objective), simpler-alternative discipline, plan-formation diagnosis, action verdicts (PROCEED/SHRINK/SPLIT/DEFER/KILL)…
sync-decisions
NOTE: this skill requires connected docs MCPs with WRITE access (Notion, Confluence, Google Docs), which are typically only present in Cowork — the Code variant exists for parity but most users will want the Cowork variant. Mirror approved decisions from the knowledge folder out to a connected docs MCP (Notion…
extract-doc
NOTE: this skill requires connected docs MCPs (Notion, Google Docs, Confluence, Box, Egnyte), which are typically only present in Cowork — the Code variant exists for parity but most users will want the Cowork variant. Pull insights from a single doc or page (Notion, Google Doc, Confluence, etc.) into the standard…
meeting-notes
NOTE: paste-text fallback works without MCPs, but docs MCPs (Notion, Confluence, Granola) are typically only connected in Cowork — the Cowork variant has better fidelity for MCP-sourced meetings. Fold a meeting transcript or notes into structured intake. Use when user says '/meeting-notes', 'capture meeting notes'…
applying-brand-guidelines
Apply consistent corporate branding and styling to generated documents, including colors, fonts, layouts, and messaging. Use when the user needs branded deliverables or asks to follow company design standards.