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/othmanadi/mddesign/agents-mdgit clone --depth 1 https://github.com/OthmanAdi/MDDesignWhat 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 | $0.00572 | $0.00572 |
| Opus 5 | $0.00286 | $0.00286 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
MDDesign 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — MDDesign
Orientation file for any coding agent working in this repo or in a project that has MDDesign installed.
What MDDesign is
An orchestrator plugin. It composes planning-with-files and DESIGN.md (both unchanged) and adds memory routing, agent-team dispatch, session handoff, and code-to-DESIGN.md harvest with critique.
What MDDesign is not
A replacement for any of those tools. If you find yourself rewriting planning-with-files behavior, the DESIGN.md spec, or the code-memory-router API, stop. That is out of scope.
Files in a project that uses MDDesign
| File | Owner | MDDesign access |
|---|---|---|
task_plan.md |
planning-with-files | read only |
findings.md |
planning-with-files | append to ## Design Context only |
progress.md |
planning-with-files | append to ### Phase <id> Result only |
DESIGN.md (root) |
user OR /mddesign:harvest |
read; write only via /mddesign:harvest and /mddesign:fix |
DESIGN.md.critique.md |
design-harvest |
full ownership |
.agents/memory/scratch/ |
memory-layer |
full ownership |
Hook lifecycle
| Hook | What it does |
|---|---|
| SessionStart | Detect planning-with-files + DESIGN.md, run catchup, nudge /mddesign:harvest if UI files but no DESIGN.md. |
| UserPromptSubmit | If active phase mentions UI keywords and DESIGN.md exists, fire design-bridge to inject the relevant tokens into findings.md. |
| PreToolUse | HITL gate at named checkpoints (UI file writes, subagent dispatch, MemPalace promotion, DESIGN.md writes). |
| Stop | Run memory-keeper to classify session output and promote stable rationale to MemPalace via HITL. |
Subagents
| Name | Purpose |
|---|---|
planner |
Drafts a PhaseSpec from a plan phase. |
executor |
Consumes a PhaseSpec, returns a structured result. |
reviewer |
HITL surrogate when auto-approve is on. |
memory-keeper |
Classifies session output into scratch / WHERE / WHY tiers. |
design-archeologist |
Long-running codebase scan for /mddesign:harvest. |
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 · 48 lines · 572 tokens per session scan A 80bfa4b05c45
MDDesign AGENTS.md is an instructions file published in the GitHub repository OthmanAdi/MDDesign (13 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 572 tokens to every session, about $0.0029 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
crewplane AGENTS.md
Instructions for crewplaneai/crewplane, covering agents.md, repo facts, read first, repo map and project heuristics.
codex-harness-javascript AGENTS.md
Instructions for thuandiep1707/codex-harness-javascript, covering codex multi-agent delivery system, system truths, public workflow registry vs internal capabilities, public workflows and internal capabilities.
AgentsMesh CLAUDE.md
Claude Code instructions for AgentsMesh/AgentsMesh, covering claude.md, project overview, components, development environment and quick start.
crewplane copilot-instructions.md
Instructions for crewplaneai/crewplane: Use AGENTS.md as the canonical repository instructions.
crewplane CLAUDE.md
Instructions for crewplaneai/crewplane, a project described as: Run reviewable, resumable coding-agent workflows across Claude Code, Codex, Gemini, GitHub Copilot CLI, or any CLI. You define the stages in Markdown; Crewplane runs the workflow, agents do the work, and every handoff stays on disk.
crewplane GEMINI.md
Instructions for crewplaneai/crewplane, a project described as: Run reviewable, resumable coding-agent workflows across Claude Code, Codex, Gemini, GitHub Copilot CLI, or any CLI. You define the stages in Markdown; Crewplane runs the workflow, agents do the work, and every handoff stays on disk.