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/12-studio/tackl/agents-mdgit clone --depth 1 https://github.com/12-Studio/TacklWhat 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 | $0.02897 | $0.02897 |
| Opus 5 | $0.01448 | $0.01448 |
| Sonnet 5 | $0.00579 | $0.00579 |
| Haiku 4.5 | $0.00290 | $0.00290 |
Grade A, and why
Tackl 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 2d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working in a Tackl project. Tool-agnostic — read by Cursor, Claude Code, Copilot, Zed, Aider, Gemini CLI and any tool that supports the agents.md convention.
Human-facing docs live in docs/ and README.md; deep-dive
skills live in skills/ (see the end of this file).
The one rule that trips agents up most
There is exactly one semantic component: the polymorphic Div. Per-tag components
(Section, Main, H1, P, Nav, …) do not exist — never import them.
import { Div } from '@tackl';
<Div as='section' $pad>…</Div>
<Div as='h1' $m='2/6' $l='3/9'>Heading</Div>
Pick the tag with the as prop, or fix it in a styles file with .attrs:
export const Jacket = styled(Div).attrs({ as: 'header' })(/* … */);
Div is a real styled.div, so it accepts spacing props ($mar, $pad, …), responsive
grid-span props ($s…$uber), and every normal HTML attribute — all fully typed.
Imports & aliases
| Import | Use for | Never write |
|---|---|---|
import { Div, bp, bpd, alpha, getBrand, … } from '@tackl' |
Primitives, breakpoints, theme getters | import { Section } from '@tackl' (doesn't exist) |
import { headlineL, bodyL } from '@tackl/type' |
Typography styles | import … from '@/theme/tackl/type' |
import Grid from '@waffl' |
The grid container (default import) | import { Grid } from '@waffl', deep paths, import { Waffl } |
import { fetchContent, GET_HOME } from '@cms' |
CMS data | importing a CMS adapter folder directly |
When editing existing files, normalise any legacy imports to the forms above.
Writing a component
Each component is a folder under src/components/ComponentName/:
index.tsx # the component — logic and markup only
styles.ts # ALL styled-components for this component
interface.ts # prop types
Component.stories.tsx # optional Storybook story
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.
- 2d ago First seen · 257 lines · 2,897 tokens per session scan A 660f7d13d984
Tackl AGENTS.md is an instructions file published in the GitHub repository 12-Studio/Tackl (10 stars, last pushed 7d ago), licensed MIT. It adds 2,897 tokens to every session, about $0.0145 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 2026-08-31.
Other instructions, from other repositories
Next-js-Boilerplate AGENTS.md
AGENTS.md instructions for ixartz/Next-js-Boilerplate, covering agents, principles, token efficiency, commands and git commits.
satus AGENTS.md
Instructions for darkroomengineering/satus, covering agents.md - satus engineering standards, stack, enforced rules (ci fails without these), oxlint rules and typescript strict flags (all active in tsconfig.json).
satus CLAUDE.md
Instructions for darkroomengineering/satus, covering satus - ai agent guide and claude code notes.
b2b-saas-starter AGENTS.md
Instructions for brandhaug/b2b-saas-starter, covering b2b saas starter, intent node index, setup, dependencies and cross-cutting rules.
Next-js-Boilerplate CLAUDE.md
Claude Code instructions for ixartz/Next-js-Boilerplate, a project described as: 🚀🎉📚 Nextjs Boilerplate and Starter with App Router and Page Router support, Tailwind CSS 4 and TypeScript ⚡️ Made with developer experience first: Next.js 16 + TypeScript + ESLint + Prettier + Drizzle ORM + Husky + Lint-Staged + Vitest…
b2b-saas-starter CLAUDE.md
Instructions for brandhaug/b2b-saas-starter, a project described as: Cloudflare-first B2B SaaS monorepo starter. TanStack Start, Effect v4, Drizzle on D1, Better Auth, Alchemy v2, REST + MCP, React Email, Storybook, Vitest, Playwright, oxlint, oxfmt, Turbo, Bun.