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/agentsorg/design-engineering/agents-mdgit clone --depth 1 https://github.com/AgentsORG/design-engineeringWhat 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 | $0.03091 | $0.03091 |
| Opus 5 | $0.01545 | $0.01545 |
| Sonnet 5 | $0.00618 | $0.00618 |
| Haiku 4.5 | $0.00309 | $0.00309 |
Grade A, and why
design-engineering 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repo-level operating guidance for AI agents working in this codebase. Pairs with SOUL.md, which carries identity (voice, stance, taste lineage). This file is the what / how; SOUL.md is the who / why. Read both on cold start.
What this repo is
A single agent skill packaged as a skill graph — one root SKILL.md (the Map of Content) plus a references/ folder of atomic, wikilinked nodes organised into themed subfolders (philosophy/, motion/, typography/, surface/, components/, layout/, anti-patterns/, meta/) and an evals/ folder for Perplexity-style Step-0 evals. A sibling agents/ directory ships six workflow subagents that map to the highest-value design-engineering tasks. The skill encodes design engineering knowledge.
Since v2.0.0 the repo is organised around four primitives: Knowledge (skills/design-engineering/, Agent Skills spec), Package (root plugin.json, Agent Plugins v1.0.0), Runtime (agent/ + evals/, the eve framework), and Client extensions (agents/, commands/, and the per-host manifest dirs, declared under reverse-domain namespaces in plugin.json extensions). The knowledge is canonical; everything else delivers it. agent/skills/ is generated by scripts/sync-skills.mjs — never edit it; edit skills/design-engineering/ and re-sync.
The graph is intentionally Obsidian-compatible: installers can open this repo as a vault to navigate clusters in the graph view and edit nodes in place. The recommended companion is kepano/obsidian-skills. Preserving that compatibility is a constraint on every edit (see rule 6).
When editing this repo
1. Edit atomic nodes, not the SKILL.md. The SKILL.md is a map. Real content lives in references/<theme>/. If you're adding new knowledge, drop the atomic node into the matching themed subfolder and link it from that theme's MOC-<theme>.md. Only update SKILL.md when adding a new top-level topic (which means adding a whole new theme folder).
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 · 129 lines · 3,091 tokens per session scan A b86631dce60c
design-engineering AGENTS.md is an instructions file published in the GitHub repository AgentsORG/design-engineering (21 stars, last pushed 10d ago), licensed MIT. It adds 3,091 tokens to every session, about $0.0155 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
naksha-studio copilot-instructions.md
Instructions for Adityaraj0421/naksha-studio, covering naksha design team — github copilot, activation triggers, the design team, design rules for code generation and css custom properties (always use these patterns).
skills AGENTS.md
Instructions for scenario-labs/skills, covering agents.md, what this repo is, layout, public content only and authoring contract.
Omni-Rewriter AGENTS.md
Instructions for WayneJin0918/Omni-Rewriter: Maintainer and coding-agent conventions live in docs/AGENTS.md. Also see .cursor/skills/omni-rewriter-h3-pe/SKILL.md, .cursor/skills/omni-rewriter-model-contribution/SKILL.md, and .cursor/skills/omni-rewriter-promo-pipeline/SKILL.md.
tapq CLAUDE.md
Instructions for spaceamoeba-t/tapq, covering tapq, testing and runtime.
generative-media-skills AGENTS.md
Instructions for calesthio/generative-media-skills, covering agent instructions, non-negotiable rules and allowed consistency.
designpowers GEMINI.md
Gemini CLI instructions for Owl-Listener/designpowers, covering designpowers, mandatory: welcome sequence first, skills, agents and notes for gemini cli.