Babysitter is a workflow engine for AI coding agents that enforces predefined steps, quality checks, human approvals, and decision records. It is used to coordinate complex, repeatable agent workflows across supported coding tools. The catalogue contains skills, agents, instructions, settings, a plugin, and an MCP integration for its workflow.
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/a5c-ai/babysitter/researchgit clone --depth 1 https://github.com/a5c-ai/babysitterWrote 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/a5c-ai/babysitter/research)<a href="https://agentmods.dev/agents/a5c-ai/babysitter/research"><img src="https://agentmods.dev/badge/agents/a5c-ai/babysitter/research.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 | $0.00000 | $0.01524 |
| Opus 5 | $0.00000 | $0.00762 |
| Sonnet 5 | $0.00000 | $0.00305 |
| Haiku 4.5 | $0.00000 | $0.00152 |
Grade A, and why
research 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 5d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wshobson/agents
Repository: https://github.com/wshobson/agents
Stars: 33,494 ⭐
License: MIT
Language: Python
Archetype: Claude Code Multi-Agent Orchestration Framework
Processing Date: 2026-04-13
Overview
A comprehensive production-ready system combining 182 specialized AI agents, 16 multi-agent workflow orchestrators, 149 agent skills, and 96 commands organized into 77 focused, single-purpose plugins for Claude Code. This represents one of the largest organized collections of agent orchestration patterns and workflows.
Repository Structure
wshobson/agents/
├── .claude-plugin/ # Claude Code plugin configuration
├── plugins/ # 77 focused plugins (main content)
│ ├── accessibility-compliance/
│ ├── agent-orchestration/
│ └── ...
├── docs/ # Comprehensive documentation
│ ├── plugins.md # Plugin reference
│ ├── agents.md # Agent reference
│ ├── agent-skills.md # Skills documentation
│ ├── usage.md # Usage patterns
│ └── architecture.md # Design principles
└── tools/ # Supporting tooling
Key Features & Architectural Patterns
Granular Plugin Architecture
- 77 focused plugins optimized for minimal token usage and composability
- Average 3.6 components per plugin (follows Anthropic's 2-8 pattern)
- Each plugin completely isolated with its own agents, commands, and skills
- Install only what you need - no unnecessary resources loaded into context
Agent Orchestration Models
- 182 specialized agents across domain expertise areas
- 16 workflow orchestrators for complex multi-agent operations
- Progressive disclosure - skills load knowledge only when activated
- Three-tier model strategy for Opus 4.6, Sonnet 4.6 & Haiku 4.5
Skills System (149 Skills)
- Modular knowledge packages with progressive disclosure
- Token efficiency through selective loading
- Specialized expertise across domains
- Compatible with agent orchestration patterns
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.
- 5d ago First seen · 161 lines · 0 tokens per session scan A 35718745bd12
research is an agent published in the GitHub repository a5c-ai/babysitter (1,765 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,524 tokens. 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 agents, from other repositories
tech-lead
Technical lead agent – PR review/approval/merge, blocker resolution, and architecture/trade-off review aligned with Jira outcomes.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
rn-code-reviewer
Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…
implementer
Use when the implementation plan needs to be executed slice by slice. A seasoned coding expert that reads the plan, follows TDD discipline, executes one vertical slice at a time, and commits each slice atomically when its tests pass. Dispatched during the Implement phase.
security-reviewer
보안 취약점 전문 분석. 인프라 우선 접근(시크릿→의존성→CI/CD→LLM→코드). OWASP Top 10 + STRIDE. "보안 리뷰", "security review", "취약점 분석" 요청에 자동 실행.
database-mysql
MySQL database specialist. Schema design, query optimization, migrations. Runs on "database design", "MySQL query", "schema optimization" requests.