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/hermesgit 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/hermes)<a href="https://agentmods.dev/agents/a5c-ai/babysitter/hermes"><img src="https://agentmods.dev/badge/agents/a5c-ai/babysitter/hermes.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 | $0.00350 |
| Opus 5 | $0.00000 | $0.00175 |
| Sonnet 5 | $0.00000 | $0.00070 |
| Haiku 4.5 | $0.00000 | $0.00035 |
Grade A, and why
hermes 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.
What it actually says
Hermes
Adapter for Nous Research's Hermes agent CLI.
Install
adapters install hermes
Supported on macOS, Linux and Windows.
Auth
Hermes is multi-provider; the adapter accepts any of:
OPENROUTER_API_KEYANTHROPIC_API_KEYOPENAI_API_KEYNOUS_API_KEYGOOGLE_API_KEYGITHUB_TOKEN
Config file (YAML): ~/.hermes/cli-config.yaml.
Minimal run
adapters run hermes --prompt "Summarize the latest commits"
Notable flags
--model <id>— defaulthermes-3-llama-3.1-405b.--prompt <text>— forwarded prompt.--auto-approve— emitted whenapprovalMode: 'yolo'.
Session files
- Location:
~/.hermes/sessions/*.jsonl - JSONL; standard parser.
Plugins
Plugin support: no. Use MCP servers for extensibility.
MCP Servers
adapters mcp install hermes <mcp-server>
adapters mcp list hermes
Registry: https://modelcontextprotocol.io
Capabilities
Tool calling with parallel calls, tool-call streaming, text streaming, 128k context.
Known limitations
- No thinking / reasoning streaming.
- No JSON mode or structured output.
- No image or file input.
- Config is YAML and global-only.
- Plugin install/list/uninstall via
adapters pluginis not supported.
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 · 66 lines · 0 tokens per session scan A c3926bcb9ee6
hermes 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 350 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.
progressive-disclosure-source
This file is the source of truth for the structure and maintenance approach.
static-analysis
Which static analyzers this repository uses, how to triage and suppress findings, and how automation config (Renovate, pinned tool versions, GitHub Actions) should be kept. Java code style itself lives in Java style & design preferences.