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 instructions/schroedernathan/clarity/agents-mdgit clone --depth 1 https://github.com/SchroederNathan/clarityWrote 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/instructions/schroedernathan/clarity/agents-md)<a href="https://agentmods.dev/instructions/schroedernathan/clarity/agents-md"><img src="https://agentmods.dev/badge/instructions/schroedernathan/clarity/agents-md.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 | $0.01565 | $0.01565 |
| Opus 5 | $0.00783 | $0.00783 |
| Sonnet 5 | $0.00313 | $0.00313 |
| Haiku 4.5 | $0.00156 | $0.00156 |
Grade A, and why
clarity AGENTS.md 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 4d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expo HAS CHANGED
Read the exact versioned docs at https://docs.expo.dev/versions/v57.0.0/ before writing any code.
The design system
Every visual value comes from one place: constants/theme.ts. Read it before styling anything.
import { colors, radius, spacing, springs, type } from '@/constants/theme';
import { useTheme } from '@/hooks/use-theme';
import { GlassSurface, PrimaryButton, SectionHeader, ThemedText } from '@/components/ui';
Four rules, in the order they get broken:
- No hardcoded visual values. No hex colors, no
fontSize, no raw spacing or radius numbers outsideconstants/. A value used twice is a token. A genuine one-off (an optical nudge on a glyph) may stay inline with a comment saying why — that is the only exemption, and the audit below counts the rest. - Colors resolve through
useTheme(), neveruseColorScheme()plus a locallight/darkmap. That pattern is what gave the app two greens, six card radii, and seven grays. - Text is
<ThemedText variant=… tone=… />. Pick a ramp step and an ink tone;weightoverrides the step's face. Nothing else names afontSize. - Frosted cards are
<GlassSurface>, not a hand-rolledisLiquidGlassAvailable()branch. Exception: a card whose child needs its own glass must render<GlassSurface style={StyleSheet.absoluteFill} />as an absolute sibling, because nested glass does not render on iOS 26.
Components import tokens; screens import components. A screen using spacing to lay out its own children is fine. A screen defining a button color is drift.
Extracting a component
Promote a view into components/ui/ only when all three hold: it appears in two or more screens, it has a nameable role, and its API is smaller than its implementation. Until then it stays where it is. Never wrap a platform component that already carries the design language (Switch, stack headers, @expo/ui views) just to route it through the system.
Auditing for drift
The whole point is that these stay near zero. Run from the repo root:
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.
- 4d ago First seen · 94 lines · 1,565 tokens per session scan A 633a24190ce6
clarity AGENTS.md is an instructions file published in the GitHub repository SchroederNathan/clarity (316 stars, last pushed today), licensed MIT. It adds 1,565 tokens to every session, about $0.0078 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 instructions, from other repositories
uniwind AGENTS.md
AGENTS.md instructions for uni-stack/uniwind, covering agent instructions and checks.
react-native CLAUDE.md
Claude Code instructions for storybookjs/react-native, covering development commands, initial setup, development, story generation and testing.
react-native-boilerplate CLAUDE.md
Claude Code instructions for wataru-maeda/react-native-boilerplate, covering claude ai development guide, project context, always use these built-in features, configuration & environment and theme & styling.
expo-targets AGENTS.md
AGENTS.md instructions for csark0812/expo-targets, covering agents, product posture, sealed zones, docs ssot and safe commands.
expo_boilerplate CLAUDE.md
Instructions for chohra-med/expo_boilerplate, covering claude.md — mobilelauncher lt, 🌿 branches — the trunk is development, there is no main, project skill, what this project is and the master rules.
leclap AGENTS.md
Instructions for heristop/leclap, covering agents.md, project overview, repository layout, setup and commands.