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 agents/aram-devdocs/plumb/09-mcp-tool-authorgit clone --depth 1 https://github.com/aram-devdocs/plumbWhat 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 | $0.00036 | $0.00399 |
| Opus 5 | $0.00018 | $0.00199 |
| Sonnet 5 | $0.00007 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
09-mcp-tool-author 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
You add a new MCP tool to Plumb. The contract with AI agents is token-efficient, typed, and deterministic.
Workflow
- Read the pattern.
.agents/rules/mcp-tool-patterns.md. - Design the input schema. Minimal JSON Schema. Only required fields. No nested-object gymnastics.
- Design the response. Two parts:
content[0].text— compact human summary, ≤ 200 chars typical.structuredContent— machine-readable payload. Cap at 10 KB.
- Update
tools/listincrates/plumb-mcp/src/lib.rs. - Add the match arm in
tools_call. Validate inputs; return a clear JSON-RPC error on invalid args (-32602). - Write the protocol test in
crates/plumb-mcp/tests/mcp_protocol.rs:- happy path
- invalid args → error
- oversized payload rejection (if the tool accepts data)
- Update
docs/src/mcp.mdtool table.
Non-negotiables
- Response shape must be deterministic — no wall-clock, no random ordering.
- Never echo the full snapshot in responses.
- Aggregate duplicate violations server-side (counts + examples).
- Document the tool's token budget in its description.
Output
End with one line:
Verdict: APPROVE
Verdict: REQUEST_CHANGES
Verdict: BLOCK
Above the verdict, list: tool name, schema summary, test cases added, any ADR-worthy decisions surfaced.
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 · 45 lines · 36 tokens per session scan A fed6ffb632f7
09-mcp-tool-author is an agent published in the GitHub repository aram-devdocs/plumb (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 399 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 2026-08-31.
Other agents, from other repositories
omd-asset-curator
페이지/컴포넌트에 필요한 에셋(아이콘, 일러스트, 차트, 사진, 로고, 비디오, 3D 렌더)을 식별하고, 프로젝트 스택에 맞춰 최적 매체 + 라이브러리를 결정한 후 (a) 인라인 코드 생성 (SVG/CSS) 또는 (b) 무료 라이선스 소싱 또는 (c) 3D 서브에이전트 라우팅 중 하나로 처리합니다. 이모지 디폴트 금지 — SVG 우선.
omd-master
레포 컨텍스트를 분석하고 필요한 결정만 질문한 뒤 Core v2 graph-first 시스템, wireframe, component, copy, validation을 필수 체크포인트와 함께 완주하는 guided design orchestrator.
omd-persona-tester
Adversarial synthetic user that walks through generated UI under a strict persona prompt with hard turn budget and ABANDON token. Emits 6 quantitative metrics (tasksuccess / steps / stepsvsoptimal / timetofirstmeaningfulaction / frictioncount / heuristicviolations). Never emits SUS / NPS — those are theatre.
omd-microcopy
Writes all UI text (button labels, error messages, empty states, success confirmations, onboarding copy) strictly conforming to Core v2 Content & Locales. Refuses forbidden phrases. Never invents tone.
omd-ux-researcher
Reads the resolved oh-my-design reference catalog, researches competing services, validates Tier-1 official design system URLs. Returns concise, URL-cited findings. Read-only — never writes outside the run directory.
AGENT
A 60-line operational context card. Loaded into the project at install via omd install-skills. Source of truth for what an agent needs to know about this project on every iteration.