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/claudegit 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/claude)<a href="https://agentmods.dev/agents/a5c-ai/babysitter/claude"><img src="https://agentmods.dev/badge/agents/a5c-ai/babysitter/claude.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 | $0.00552 |
| Opus 5 | $0.00000 | $0.00276 |
| Sonnet 5 | $0.00000 | $0.00110 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade B, and why
claude scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Credentials live in `~/.claude/settings.json`. How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code
Adapter for Anthropic's Claude Code CLI.
Install
adapters install claude
Minimum CLI version: 1.0.0. Supported on macOS, Linux and Windows.
Auth
Two auth methods are supported:
- API key — set
ANTHROPIC_API_KEYin your environment. - Browser login — run
claudeonce interactively to complete OAuth.
Credentials live in ~/.claude/settings.json.
Minimal run
adapters run claude --prompt "Summarize README.md"
Programmatic:
import { createClient } from '@a5c-ai/adapters';
const client = createClient();
const handle = await client.run({ agent: 'claude', prompt: 'Hello' });
for await (const ev of handle.events()) console.log(ev);
Notable flags
The adapter forwards these RunOptions to the CLI:
--output-format jsonl(always, for streaming parse)--model <id>— e.g.claude-sonnet-4-20250514orclaude-opus-4-20250514--resume <sessionId>— resume a prior session- Thinking effort:
low | medium | high | max - Approval modes:
yolo,prompt,deny
Session files
- Location:
~/.claude/projects/<project-hash>/*.jsonl - Format: JSONL, one event per line
- Resume and fork are both supported (
canResume,canFork).
Plugins
Plugin support: yes. Claude Code has a full plugin ecosystem with marketplace.
Native Plugin Management
adapters plugin install claude <plugin>
adapters plugin list claude
adapters plugin marketplace claude
MCP Servers
adapters mcp install claude <mcp-server>
adapters mcp list claude
Registry: https://modelcontextprotocol.io for MCP servers.
Plugin marketplace: Available through claude plugins marketplace.
Capabilities
Streaming text, tool calls and thinking; parallel tool calls; image input; file attachments; subagent dispatch (up to 10 parallel). Supports Skills and AGENTS.md.
Known limitations
- Image output is not supported.
- Tool approval is required by default — use
approvalMode: 'yolo'to auto-approve in trusted environments. - Session file paths are keyed by a hash of the project directory; moving a repo invalidates resume.
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 · 82 lines · 0 tokens per session scan B 1b1c90d58b86
claude is an agent published in the GitHub repository a5c-ai/babysitter (1,769 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 552 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
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…
design-author
Use after research is complete to draft the approach before any code is written. Drafts a 200-line design document covering current state, desired end state, patterns to follow, and decisions made. Resolves its own open questions autonomously, recording each as an explicit, auditable assumption in the design.
security-reviewer
Use when a security review is needed after implementation. Applies OWASP-style checks with fresh context. Critical findings are a hard gate — they block shipping until resolved. Example triggers — "security review", "check for vulnerabilities", "audit this code for security issues".
planner
Use after the structure is produced to create the tactical implementation plan. Translates each vertical slice in 7-structure.md into precise file-level steps with acceptance test mappings. The plan is a tactical artifact for the implementer — neither the structure nor the plan is human-reviewed (the design passed…
technical-writer
Use after implementation to review whether project documentation needs updating. Reads the diff and compares against existing docs to identify gaps and stale content. Produces a structured report — does not rewrite docs itself. Example triggers — "check if docs need updating", "documentation review", "are the docs…
verifier
Use when comprehensive verification checks need to run before completion. Runs all available checks (format, lint, type check, build, tests) in speed order and produces an evidence-based report. Example triggers — "run all checks", "verify the build", "pre-flight checks", "does everything pass".