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/internet-development/www-sacred/agents-mdgit clone --depth 1 https://github.com/internet-development/www-sacredWrote 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/internet-development/www-sacred/agents-md)<a href="https://agentmods.dev/instructions/internet-development/www-sacred/agents-md"><img src="https://agentmods.dev/badge/instructions/internet-development/www-sacred/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 | $0.03243 | $0.03243 |
| Opus 5 | $0.01622 | $0.01622 |
| Sonnet 5 | $0.00649 | $0.00649 |
| Haiku 4.5 | $0.00324 | $0.00324 |
Grade A, and why
www-sacred 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Orientation for any agent working in www-sacred. Read this before touching code.
What this repo is
www-sacred (npm package srcl) is an open-source React component library with terminal aesthetics. It is consumed in two ways:
- A Next.js 16 / React 19 site at
sacred.computerthat renders every component in a kitchen sink atapp/page.tsx. - Simulacrum, a zero-dependency CLI framework under
scripts/cli/lib/(and a snake_case Python mirror underscripts/python/sacred_cli/) so the same layouts can render in a terminal.
Colors flow from one source: scripts/cli/colors.json. That file holds the terminal-tested palette. global.css mirrors it as --ansi-* primitives and builds --theme-* tokens on top. The OKLCH tint themes in global.css are a web-only derivation. When a color changes, it changes in colors.json first.
Repo map
app/— Next.js App Router.app/page.tsxis the kitchen sink. The/llm/*routes serve docs as markdown and component source as plain text so agents can fetch them without cloning.components/— Sacred React components. Readcomponents/AGENTS.mdfirst when picking a component.components/examples/has larger demo surfaces.SimpleTableis the table for CLI ports (maps ontoformatRow+cardHeaderRow).Windowis the React peer of the CLI window frame.common/— Constants and utilities shared across components.modules/— Stand-alone, dependency-free modules: the vendoredhotkeys/library plus a few vendored Node helpers (cors.ts,vary.ts,object-assign.ts).scripts/cli/— Simulacrum, the sacred CLI framework (TypeScript, zero dependencies, run viatsx).lib/is the framework,lib/__tests__/is the vitest suite (and thedump_reference.tsfixture generator),templates/is the canonical TS template,colors.jsonis the shared palette.scripts/python/— Simulacrum's Python mirror.sacred_cli/is the package,sacred_cli/__tests__/is the unittest suite (and the parity test against the JS fixture),templates/is the canonical Python template.scripts/test_python.ts— TypeScript orchestrator fornpm run test:python. Probes forpython3, regenerates the TS fixture, then invokespython3 -m unittest discover. Skips with a warning ifpython3is missing.skills/— Four porting skills (TS CLI, Python CLI, React-to-React, hostile React host). Readskills/*/SKILL.mdbefore porting..workdir/— Read-only reference material from sibling projects. Never edit, never ship.
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 · 118 lines · 3,243 tokens per session scan A 938032650591
www-sacred AGENTS.md is an instructions file published in the GitHub repository internet-development/www-sacred (1,555 stars, last pushed 12d ago), licensed MIT. It adds 3,243 tokens to every session, about $0.0162 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
oh-my-design AGENTS.md
AGENTS.md instructions for kwakseongjae/oh-my-design, covering agents.md — oh-my-design, repository quick map, build / test / lint, design harness mode and entrypoint.
starwind-ui AGENTS.md
Instructions for starwind-ui/starwind-ui, covering agents.md, project shape, useful commands and contribution conventions.
oh-my-design CLAUDE.md
Claude Code instructions for kwakseongjae/oh-my-design, a project described as: Give your AI coding agent a design system. One command installs 400+ quality-graded company DESIGN.md references + skills into Claude Code, Codex, Cursor, and OpenCode. Free, MIT, zero AI calls.
aicanvas CLAUDE.md
Claude Code instructions for uiNerd16/aicanvas, covering ai canvas — global rules, what this project is, how work is organized, secrets & credentials — this is an open-source repo and tech stack.
animal-island-ui AGENTS.md
AGENTS.md instructions for guokaigdg/animal-island-ui, covering agents.md — working in this repository, read first, by task, verification, content that must be kept in sync and ground rules.
ns-ui AGENTS.md
AGENTS.md instructions for nikolas-sapa/ns-ui, covering agents.md — working inside this repo, structure, autoplay — how a card demonstrates itself, descriptor schema and driver constraints (don't regress these).