Borrowing it
Nothing to install: this file belongs to ganapativs/microcharts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ganapativs/microcharts/main/CLAUDE.mdgit clone --depth 1 https://github.com/ganapativs/microchartsWrote 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/ganapativs/microcharts/claude-md)<a href="https://agentmods.dev/instructions/ganapativs/microcharts/claude-md"><img src="https://agentmods.dev/badge/instructions/ganapativs/microcharts/claude-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 5.1 | $0.05706 | $0.05706 |
| Opus 5 | $0.02853 | $0.02853 |
| Sonnet 5 | $0.01141 | $0.01141 |
| Haiku 4.5 | $0.00571 | $0.00571 |
Grade B, and why
microcharts CLAUDE.md scanned grade B with 1 finding 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 8d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
options. The craft shows in the output; the code and copy don't lecture about it. How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
microcharts — contributor & agent guide
Word-sized charts for React: zero runtime dependencies, ~2–7 kB interactive · ~1–4 kB static per chart, accessible by
default, handcrafted-feeling. They're built to sit inside an interface — a sentence, a table cell, a KPI card, a tab
header, a streamed AI reply — and to be safe for a model to emit and a person to read. Package:
@microcharts/react.
This file is the working contract for anyone (human or AI) changing the code. The rules below are not style preferences — several are enforced in CI, and violating them is a bug.
Design principles
- Earn every mark: each pixel must encode data, state, structure, or a useful interaction cue.
- First read instant, second read rewarding: clarity at a glance may reveal finer structure on inspection.
- Prefer uncommon questions over uncommon shapes: add a chart only when it answers a practical decision the catalog cannot already answer well.
- Delight without lying: motion, rhythm, texture, and direct manipulation may delight, but never change what the data means.
- Tiny size is a design material, not a limitation: composition, contrast, and summaries must survive the smallest supported context.
Charts must remain excellent in light, dark, print, and dense product contexts. "Modern" means sharper thinking and better behavior — not neon glow, glass, dashboard chrome, or decorative complexity.
Non-negotiables (violating any of these is a bug)
- Zero runtime dependencies.
dependencies: {}forever, CI-enforced. React is a peer:"react": "^18.0.0 || ^19.0.0". Scales, paths, easing, color, stats, summaries — all in-house. All chart types ship in the one@microcharts/reactpackage. Any third-party dev-dependency must be verified actively maintained before adoption. - Budgets are CI gates, applied in this order. (1) Per-subpath budget: every subpath carries its own limit in
scripts/size-budgets.json, set to measured + max(50 B, 2%);styles.css≤ 12 kB..size-limit.jsonis generated (scripts/gen-size-limits.mjsfrom that file), never hand-edited. (2) Regression diff: every PR is diffed against its base branch —scripts/size-snapshot.jsonrecords the measured gzip bytes of all 218 subpaths, CI re-measures against a fresh build (size-snapshot.mjs --check), and thesize-diffjob replies with a per-subpath table. Growth over 1% on any subpath fails; regenerate withpnpm build && pnpm size:snapshot, and label the PRsize-increase-approvedwhen an increase is deliberate. (3) Admission bar for a NEW chart: static ≤ 3 kB (≤ 2 kB target, "Delta-class" ≤ 1.5 kB), interactive ≤ static + 3.25 kB, ≤ ~6 SVG nodes typical, 0 client JS for static charts in RSC. (4) Catalog ceiling: static 4.35 kB / interactive 7 kB. The interactive wall is hard — no subpath crosses it, and no sign-off raises it, because "~2–7 kB interactive" is quoted in the README, the docs and the package description.sparklinedefines the top of both scales (4256 / 6973 measured) and its interactive budget is pinned at the wall: 7000 B, 27 B of headroom. Growing that entry fails the gate on purpose — buy room by shrinking it, never by raising the number.
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.
- 8d ago First seen · 263 lines · 5,706 tokens per session scan B ee82980bc4e2
microcharts CLAUDE.md is an instructions file published in the GitHub repository ganapativs/microcharts (172 stars, last pushed today), licensed MIT. It adds 5,706 tokens to every session, about $0.0285 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.