Kami is a constraint-based design system for producing polished documents and landing pages with coding agents. It supports agents that generate resumes, reports, slides, letters, changelogs, portfolios, and other templated content.
Borrowing it
Nothing to install: this file belongs to tw93/Kami. 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/tw93/Kami/main/AGENTS.mdgit clone --depth 1 https://github.com/tw93/KamiWrote 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/tw93/kami/agents-md)<a href="https://agentmods.dev/instructions/tw93/kami/agents-md"><img src="https://agentmods.dev/badge/instructions/tw93/kami/agents-md/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/instructions/tw93/kami/agents-md"><img src="https://agentmods.dev/badge/instructions/tw93/kami/agents-md.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 | $0.08839 | $0.08839 |
| Opus 5.5 | $0.03536 | $0.03536 |
| Sonnet 5.5 | $0.01768 | $0.01768 |
| Haiku 4.5 | $0.00884 | $0.00884 |
Grade A, and why
Kami AGENTS.md scanned grade A 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
deploy: verify them with `curl -sI` against the preview URL, never locally. How it starts
The opening of the file, as written. The whole thing — 539 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kami Agent Guide
Project
Kami is a document-generation skill and template system: self-contained editorial HTML
templates rendered to PDF / PPTX / PNG, plus reference specs, demo assets, and a
packaged skill archive. SKILL.md is the runtime manual for producing a document.
This file is the maintenance guide for changing the repository itself, and it records
the traps that a fresh read of the code does not reveal.
Layout
One repository, three top-level roles, and the install tools only ever copy the first:
skills/kami/is the skill and the only thing users install:SKILL.md,CHEATSHEET.md,VERSION,LICENSE,references/,scripts/, and the lightassets/(templates, diagrams, logo, the two small font files).npx skills add tw93/kamicopies exactly this directory;bash scripts/package-skill.shzips it askami/for Claude Desktop;plugins/kami/skills/kami/is a generated copy of it inside the Claude and Codex plugin. Ignored render output lives inskills/kami/assets/examples/. Every skill-relative path inSKILL.mdresolves inside this directory, so nothing here may reach up into the repo.site/is kami.tw93.fun. The Vercel project's Root Directory issite(project setting, not a file), so only this tree deploys andsite/vercel.jsonis the only Vercel config. It carries the pages,styles.css,llms.txt,robots.txt,sitemap.xml,vercel.json,.well-known/,feeds/, and the heavy showcase and demo assets. Skill facts it shows (SKILL.md, the discovery files) are generated into it, never hand-copied./SKILL.mdand/kami-skill.mdsendX-Robots-Tag: noindex: agents can still fetch the markdown, and search engines should not score that file as an HTML page.- The root holds repository tooling only:
scripts/(build_metadata.py,package-skill.sh,release_gate.py,draft-release-notes.py,tests/),assets/fonts/(the commercial TTFs; runbash skills/kami/scripts/ensure-fonts.shonce after cloning to copy them into the skill's ignoredassets/fonts/, otherwise templates fall back to jsDelivr),evals/(the end-to-end skill eval suite, see Evals below),docs/, and.github/.
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.
- yesterday Changed · -10 tokens per session 6e25a20b7dc5
- 11d ago Changed · +33 lines · +661 tokens per session b221c1b03c06
- 16d ago Changed · +3 lines · +51 tokens per session 28333623e4df
- 17d ago Changed · +42 lines · +628 tokens per session 87bea95177e2
- 1mo ago Changed · +38 lines · +662 tokens per session f57307883749
- 1mo ago Changed · +4 lines · +86 tokens per session 0ee79c740cb1
- 1mo ago Changed · +6 lines · +119 tokens per session d2db7d60fcb9
- 1mo ago Changed · +5 lines · +76 tokens per session 447c92ce5cee
- 1mo ago Changed · -1 tokens per session 56c254f6304c
- 1mo ago First seen · 408 lines · 6,567 tokens per session scan A 4036a34797ef
Kami AGENTS.md is an instructions file published in the GitHub repository tw93/Kami (12,093 stars, last pushed yesterday), licensed MIT. It adds 8,839 tokens to every session, about $0.0354 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.