Reflect is an open-source note-taking app that stores notes as Markdown files in a user-chosen folder, with daily notes, wiki links, backlinks, local search, and optional AI features. People use it to write, connect, search, synchronize, and query personal notes on Mac and iPhone. Catalogue add-ons support agent workflows such as interacting with notes through its CLI and related automation.
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/team-reflect/reflect-open/design-systemnpx skills add team-reflect/reflect-open --skill design-systemgit clone --depth 1 https://github.com/team-reflect/reflect-openWrote 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/team-reflect/reflect-open/design-system)<a href="https://agentmods.dev/skills/team-reflect/reflect-open/design-system"><img src="https://agentmods.dev/badge/skills/team-reflect/reflect-open/design-system.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 | $0.00060 | $0.00578 |
| Opus 5 | $0.00030 | $0.00289 |
| Sonnet 5 | $0.00012 | $0.00116 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
reflect-design 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 5d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read the README.md file within this skill, and explore the other available files.
If creating visual artifacts (slides, mocks, throwaway prototypes, etc), copy assets out and create static HTML files for the user to view. If working on production code, you can copy assets and read the rules here to become an expert in designing with this brand.
If the user invokes this skill without any other guidance, ask them what they want to build or design, ask some questions, and act as an expert designer who outputs HTML artifacts or production code, depending on the need.
Quick map
readme.md— the full design guide: product context, voice, visual foundations, iconography, and a file index. Start here.styles.css— link this one file to inherit every token + the Inter webfont.tokens/— colors (indigo brand + cool greys + marketing purples;.darkand.reflect-spacetheme scopes), typography, spacing/radii/shadow/motion.assets/— Inter Variable fonts, the graph app icon, logo, and graph hero image.components/— React primitives (Button, IconButton, ShortcutKey, Input, SearchField, Checkbox, Toggle, Card, Badge, Avatar, MenuItem). Each has a.prompt.mdwith usage.guidelines/— foundation specimen cards.ui_kits/app/— the notes app (daily notes, ⌘K search, tasks, map).ui_kits/marketing/— the deep-space homepage.
The one-paragraph brief
Reflect is a fast, minimalist, networked note-taking app — a writing tool where
prose is the hero and chrome is quiet. Two surfaces share one purple soul: the app
is a calm near-white (or deep-navy dark) canvas with indigo #4F46E5 as the only
saturated accent and cool grey everything-else; the marketing site is a near-black
#030014 "deep space" lit by purple glows and glassmorphic borders. One typeface:
Inter. Sentence case everywhere, no emoji, benefit-led copy. Gentle 8px radii,
mostly-flat surfaces with hairline borders, short calm motion (no bounce).
What ships with it
60 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.
- _adherence.oxlintrc.json 13 KB
- _ds_bundle.js 92 KB runs code
- _ds_manifest.json 26 KB
- assets/fonts/InterVariable-Italic.woff2 372 KB
- assets/fonts/InterVariable.woff2 337 KB
- assets/reflect-app-icon-square.png 733 KB
- assets/reflect-app-icon.png 299 KB
- assets/reflect-graph-hero.png 170 KB
- assets/reflect-logo-mark.png 4.1 KB
- components/buttons/Button.d.ts 829 B runs code
- components/buttons/Button.jsx 3.2 KB
- components/buttons/Button.prompt.md 619 B
- components/buttons/buttons.card.html 4.9 KB
- components/buttons/IconButton.d.ts 480 B runs code
- components/buttons/IconButton.jsx 1.3 KB
- components/buttons/IconButton.prompt.md 337 B
- components/buttons/ShortcutKey.d.ts 389 B runs code
- components/buttons/ShortcutKey.jsx 1.3 KB
- components/buttons/ShortcutKey.prompt.md 254 B
- components/data-display/Avatar.d.ts 351 B runs code
- components/data-display/Avatar.jsx 1.5 KB
- components/data-display/Avatar.prompt.md 229 B
- components/data-display/Badge.d.ts 294 B runs code
- components/data-display/Badge.jsx 1.3 KB
- components/data-display/Badge.prompt.md 183 B
- components/data-display/Card.d.ts 469 B runs code
- components/data-display/Card.jsx 768 B
- components/data-display/Card.prompt.md 203 B
- components/data-display/data-display.card.html 4.7 KB
- components/data-display/MenuItem.d.ts 561 B runs code
- components/data-display/MenuItem.jsx 1.6 KB
- components/data-display/MenuItem.prompt.md 293 B
- components/forms/Checkbox.d.ts 277 B runs code
- components/forms/Checkbox.jsx 1.7 KB
- components/forms/Checkbox.prompt.md 180 B
- components/forms/forms.card.html 3.7 KB
- components/forms/Input.d.ts 521 B runs code
- components/forms/Input.jsx 1.7 KB
- components/forms/Input.prompt.md 215 B
- components/forms/SearchField.d.ts 392 B runs code
- components/forms/SearchField.jsx 1.8 KB
- components/forms/SearchField.prompt.md 190 B
- components/forms/Toggle.d.ts 191 B runs code
- components/forms/Toggle.jsx 1.3 KB
- components/forms/Toggle.prompt.md 142 B
- guidelines/brand-graph.html 725 B
- guidelines/brand-logo.html 1.8 KB
- guidelines/colors-brand.html 2.6 KB
- guidelines/colors-marketing.html 3.0 KB
- guidelines/colors-neutrals.html 2.3 KB
- guidelines/colors-semantic.html 2.0 KB
- guidelines/spacing-elevation.html 2.0 KB
- guidelines/spacing-radii.html 2.1 KB
- guidelines/spacing-scale.html 2.5 KB
- guidelines/type-display.html 1.4 KB
- guidelines/type-scale.html 2.1 KB
- guidelines/type-weights.html 1.5 KB
- package.json 268 B
- readme.md 17 KB
- styles.css 1019 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.
- 5d ago First seen · 40 lines · 60 tokens per session scan A 45233f21fd44
reflect-design is a skill published in the GitHub repository team-reflect/reflect-open (1,454 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 578 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
backlog-technical-project-manager
Technical project management for Backlog.md workstreams using coordinated sub-agents. Use only when the user explicitly asks Codex to take over one or more existing Backlog.md tasks (for example: "act as TPM", "coordinate these tasks", "delegate to sub-agents"). Orchestrate planning, implementation, and finalization…
technical-writing
Write, edit, review, or audit user-facing documentation for the eve repository. Use for changes under docs/, documentation tied to eve APIs or CLI behavior, docs work based on Slack or support feedback, and requests to make eve docs clearer, more natural, or less AI-patterned while verifying claims against current…
gh-pr-description
Drafts and reviews GitHub pull request descriptions for the eve repository. Use when opening, updating, or reviewing a PR, or when summarizing a branch for reviewers.
toolkit-guide
How to triage an account and verify packaged skill resources with the toolkit CRM extension.
local-guide
The consuming agent's own guide skill.
wiki-sync
Synthesize a single source note into the vault's wiki/ folder — read the source, find or create the right wiki entry, write it back with proper frontmatter and source links. Used by Lumina's background wiki manager when a note changes.