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/webba-creative-technologies/forge/agents-mdgit clone --depth 1 https://github.com/Webba-Creative-Technologies/forgeWhat 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 | $0.01814 | $0.01814 |
| Opus 5 | $0.00907 | $0.00907 |
| Sonnet 5 | $0.00363 | $0.00363 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
forge 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Hard rules for AI code generation with Forge. Read this before writing any code.
Rule 1: Forge first, always
Before writing UI, check if Forge already has the component. The full list is in skills/forge/components.md. If Forge has it, import it. Do not reimplement.
Do not build: modals, drawers, tooltips, popovers, dropdowns, date pickers, time pickers, toasts, notifications, tables, tabs, accordions, steppers, breadcrumbs, avatars, badges, banners, toolbars, sidebars, navbars, footers, skeletons, spinners, carousels, image galleries, video players, audio players, command palettes, color pickers, sliders, tag inputs, OTP inputs, phone inputs, password inputs, mention inputs, tree views, sortable lists, calendars, timelines, charts, or cookie banners. Forge provides all of these.
Rule 2: Single import source
Always import from 'wss3-forge'. No deep imports.
// Correct
import { Button, Card, useToast } from 'wss3-forge'
// Wrong
import { Button } from 'wss3-forge/components/Button'
Rule 3: ForgeProvider is required
The app must be wrapped in ForgeProvider at the root. Without it, CSS variables are missing and every component renders unstyled. Never nest multiple providers.
import { ForgeProvider } from 'wss3-forge'
<ForgeProvider mode="dark">
<App />
</ForgeProvider>
Rule 4: Icons from Fluent UI 2 only
Icons come from @fluentui/react-icons. No react-icons, no lucide-react, no heroicons, no inline SVG when a Fluent equivalent exists.
Naming convention: {Name}{Size}{Style} where size is 12 | 16 | 20 | 24 | 28 | 32 | 48 and style is Regular | Filled.
import { ArrowRight20Regular, Heart24Filled } from '@fluentui/react-icons'
No text arrows (->, =>, →). Use ArrowRight{Size}Regular.
Rule 5: Colors via CSS variables
Use var(--...) for every color. Never hardcode hex values, RGB, HSL, or any color name.
// Correct
<div style={{ color: 'var(--text-primary)', background: 'var(--bg-secondary)' }} />
// Wrong
<div style={{ color: '#fff', background: '#181818' }} />
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 · 173 lines · 1,814 tokens per session scan A 48dc18d8d009
forge AGENTS.md is an instructions file published in the GitHub repository Webba-Creative-Technologies/forge (19 stars, last pushed 3mo ago), licensed MIT. It adds 1,814 tokens to every session, about $0.0091 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
ui-components AGENTS.md
Instructions for starc007/ui-components, covering beui v2 — agent guide, commands, layout, component catalog and components (motion category — primitives).
unity-ui-toolkit-design-system AGENTS.md
Instructions for sinanata/unity-ui-toolkit-design-system, covering agents.md, what this project is, golden rules (do not violate), use the design system in your project and repository layout.
unity-ui-toolkit-design-system copilot-instructions.md
Instructions for sinanata/unity-ui-toolkit-design-system: This repository follows the cross-tool AGENTS.md standard. Read /AGENTS.md for the full guide: the ds- class naming, the token rules, the load-bearing USS import order, build and preview commands, and the pull-request checklist.
chakra-ui CLAUDE.md
Instructions for chakra-ui/chakra-ui, covering claude's learning document - chakra ui, project overview, project structure, root directory and key packages.
gradio AGENTS.md
AGENTS.md instructions for gradio-app/gradio, covering agents.md, repository structure, pull request rules, code style and agentic contribution policy.
tamagui AGENTS.md
AGENTS.md instructions for tamagui/tamagui, covering tamagui — agent operating contract, finish what you start, then merge it back, tamagui testing guide, running tests and kitchen sink tests.