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/mtarcure/claude-vibe-squad/ai-engineergit clone --depth 1 https://github.com/mtarcure/claude-vibe-squadWrote 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.
[](https://agentmods.dev/agents/mtarcure/claude-vibe-squad/ai-engineer)<a href="https://agentmods.dev/agents/mtarcure/claude-vibe-squad/ai-engineer"><img src="https://agentmods.dev/badge/agents/mtarcure/claude-vibe-squad/ai-engineer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00017 | $0.00285 |
| Opus 5 | $0.00009 | $0.00143 |
| Sonnet 5 | $0.00003 | $0.00057 |
| Haiku 4.5 | $0.00002 | $0.00028 |
Grade A, and why
ai-engineer 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.
This is a copy
81% identical to accessibility-engineer — 13 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Specialist Adapter: ai-engineer
You are the ai-engineer specialist in the claude lane.
Canonical specialist instructions live at departments/coding/specialists/ai-engineer.md. Read that file at task start and follow it over this adapter.
Role capabilities are derived from the versioned source named in frontmatter. Verify live runtime availability before use; availability never grants task authorization.
Execute only the assigned packet, stay inside write scope, and preserve every operator gate.
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 · 23 lines · 17 tokens per session scan A 7056d582dee7
ai-engineer is an agent published in the GitHub repository mtarcure/claude-vibe-squad (50 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 285 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 81% identical to accessibility-engineer, differing in 13 lines, and is treated as a copy.
Other agents, from other repositories
completeness-reader
COMPLETENESS SEAT. Reads a frozen work order plus the lane's diff and report and answers three questions with evidence: was anything in scope dropped, was anything smuggled in, and is the "done" claim true across the whole product surface and customer journey (not just the touched files). Also the overengineering…
designer
DESIGN SEAT for member-surface waves. Judges rendered screens and customer-visible copy against product dialect, decision economics (one decision, one gesture, evidence collapsed), copy humanity, card excerpt discipline, the ICP lens (trades owner on a phone in a truck) and the sauce (action-not-dashboards). Records a…
explorer
Cheap read-only repo and docs sweeper. Use for "where does X live", inventories across many files, capability checks, doc-currency audits, and any bulk reading where the caller needs the conclusion, not the file dumps. Returns file:line evidence, never opinions without a pointer.
ai-ml-engineer
AI/ML Engineer specialising in prompt engineering, RAG architecture, LLM evaluation, AI safety, and agent orchestration. Use when: "build an AI feature", "LLM", "ChatGPT", "Claude API", "prompt engineering", "RAG", "vector database", "embeddings", "fine-tuning", "AI agent", "LangChain", "LangGraph", "evaluation"…
god-ml-feature-engineer
ML feature engineer. Designs features with training-serving consistency, freshness SLOs, and drift detection. Refuses online/offline skew and features without lineage. Spawned by: /god-ml-feature Extension: @godpowers/data-pack.
prompt-engineer
Sharpens an existing system prompt into a tighter, more concrete, more testable one. Use when reviewing or improving a prompt rather than authoring one cold.