agentmods.dev

design-pipeline: Instructions file for Codex

AGENTS.md

design-pipeline AGENTS.md is an instructions file for Codex, OpenCode from 2233admin/design-pipeline. It costs 1,062 tokens per session, scanned A, original, MIT.

Repository-specific instructions for the design-pipeline project, a packaged workflow for creating user interfaces, motion websites, and product films. They describe its policies, file locations, commands, verification steps, and conventions.

In plain words
What is it for?
Use them when modifying, checking, or extending the design-pipeline repository.
Why use it?
They give coding agents the project's local rules instead of relying only on general habits. This helps protect change history, evidence records, and existing work.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions .claude-plugin; mentions Claude Code.

This is 2233admin/design-pipeline's own configuration. It tells Codex and OpenCode how to work on design-pipeline itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything design-pipeline configures →

not rated 12repo changed 9d ago A scan 1,062 tokens original MIT
View source ↗ 2233admin/design-pipeline
Reuse

Borrowing it

Nothing to install: this file belongs to 2233admin/design-pipeline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/2233admin/design-pipeline/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/2233admin/design-pipeline

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for design-pipeline AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/2233admin/design-pipeline/agents-md/github.svg)](https://agentmods.dev/instructions/2233admin/design-pipeline/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/2233admin/design-pipeline/agents-md"><img src="https://agentmods.dev/badge/instructions/2233admin/design-pipeline/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.

agentmods 80×15 button for design-pipeline AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/2233admin/design-pipeline/agents-md"><img src="https://agentmods.dev/badge/instructions/2233admin/design-pipeline/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,062 This file is loaded in full into every session.
When invoked 1,062 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01062 $0.01062
Opus 5.5 $0.00425 $0.00425
Sonnet 5.5 $0.00212 $0.00212
Haiku 4.5 $0.00106 $0.00106

Measured 9d ago against content hash 472c83c22f71, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

design-pipeline 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 9d 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.

AGENTS.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

design-pipeline

Design and film workflow (UI, motion web, product films, PV/MAD edits) shipped as a packaged agent skill. Runtime scripts use Node.js CommonJS; the root package.json is a private maintenance workspace for evals/cases and tools/browser-automation, separate from the packaged skill. Package entry is skill/SKILL.md; stage contracts live in skill/references/stages.md, with route guidance in pipeline-reference.md; behavior specs and changes live in openspec/.

Policy

  • Change behavior only through an OpenSpec change under openspec/changes/<change-id>/; read openspec/config.yaml and that change first.
  • Extend existing gates, contracts and receipt schemas; never add a parallel gate, receipt schema, target resolver or policy digest. Delete superseded paths instead of keeping compatibility aliases or migrations.
  • Keep target, snapshot, policy digest and receipt lineage intact; when an upstream receipt changes, recompute or invalidate downstream evidence.
  • Report Component Conformance and Visual Acceptance separately; gate results never claim creative or visual acceptance.
  • Preserve unrelated working-tree changes; inspect git status before editing and never reset or discard work you did not make.

Where things are

  • CLI: node skill/scripts/designer-pipeline.cjs <command>; next reads .design-pipeline/state.json and returns one action, decide records user decisions; commands are the COMMANDS table in skill/scripts/cli-core.cjs.
  • Release and versioning rules: .github/CONTRIBUTING.md.

Running and verifying

  • Use Node.js 22.12+ and run npm ci at the repository root to install the private maintenance workspace. Run npm test for repository QA and browser-tool self-tests; never bare node --test, which discovers nested upstream fixtures.
  • Use the workspace-pinned OpenSpec CLI with npm exec -- openspec ...; run npm run specs:check for strict repository validation.
  • npm test reads ignored .env.local for BLENDER_PATH (an externally set environment value wins) and passes the shared Chrome resolver result to isolated QA. Keep machine-specific paths in .env.local, never in committed docs or source.
  • Use npm run browser:install to prepare Playwright Chromium and the HyperFrames browser. Film render checks also need ffmpeg and ffprobe on PATH; Blender is discovered via --blender, BLENDER_PATH, PATH, then supported platform locations.
  • Add each new test file to scripts/test-manifest.json, or QA never runs it.
  • List each load-bearing new file under skill/ in required of skill/references/package-resources.json; packaging ships all of skill/, and the list only makes packaging fail when a listed file goes missing.

Read the full file on GitHub · 52 lines

Changes

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.

  1. 9d ago Changed · +55 tokens per session 472c83c22f71
  2. 19d ago Changed · +14 lines · +89 tokens per session 1bc4f4d51aeb
  3. 22d ago Changed · +4 lines · +392 tokens per session 5d51a5c59c95
  4. 1mo ago First seen · 34 lines · 526 tokens per session scan A 12a084b0f6a0

Subscribe to this mod's changes

design-pipeline AGENTS.md is an instructions file published in the GitHub repository 2233admin/design-pipeline (12 stars, last pushed yesterday), licensed MIT. It adds 1,062 tokens to every session, about $0.0042 per session on Opus 5.5. 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 2026-09-29.

Building agentsClaude Codeai-agentscodex-clidesign-systemdesign-tokensfrontend-development
Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens