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 commands/othmanadi/mddesign/teamgit 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 | $0.00043 | $0.00448 |
| Opus 5 | $0.00022 | $0.00224 |
| Sonnet 5 | $0.00009 | $0.00090 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
team 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.
What it actually says
/mddesign:team
Subagent dispatch.
Subcommands
/mddesign:team dispatch <phase_id>
Auto-picks the subagent:
- Phases with "design" / "ui" / "tokens" in the title and a harvest-shaped intent →
design-archeologist - Phases with no existing PhaseSpec →
planner(returns the spec, then you re-dispatch with--agent executor) - All others →
executor
/mddesign:team dispatch <phase_id> --agent <name>
Force a specific subagent. Values:
planner— draft a PhaseSpec from the phaseexecutor— run the PhaseSpec end to endreviewer— audit another's return againstdone_whenmemory-keeper— classify recent session output (usually called by Stop hook)design-archeologist— scan codebase for/mddesign:harvest
Flow
- Read
task_plan.md, resolve the phase. - Build the PhaseSpec (team-dispatch skill logic).
- HITL gate (named checkpoint:
before_subagent_dispatch). - Call
Agenttool with the chosensubagent_type. - Parse the structured return.
- Append to
progress.mdunder### Phase <phase_id> Result. - If auto-approve is on, dispatch
reviewer.
Boundaries
- Subagents never edit
task_plan.md. - All dispatches HITL gated.
- Markdown is the shared state across agents; no in-memory store.
See skills/team-dispatch/SKILL.md for the full PhaseSpec v1 schema and dispatch logic.
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 · 44 lines · 43 tokens per session scan A 6da8528d3c6c
team is a command published in the GitHub repository OthmanAdi/MDDesign (13 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 448 once invoked, about $0.0002 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 commands, from other repositories
work
通过 v3 流程发起正式工作请求 (entry gate).
tdd
Guide Test-Driven Development workflow (Red-Green-Refactor).
verify
Run comprehensive pre-PR verification (5-phase quality check).
commit-push-pr
Create git commit, push to remote, and create/merge pull request.
gha
Analyze GitHub Actions CI failures.
handoff
Generate context handoff document for session continuity.