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 skills add a5c-ai/babysitter --skill research-first-devgit 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/skills/a5c-ai/babysitter/research-first-dev)<a href="https://agentmods.dev/skills/a5c-ai/babysitter/research-first-dev"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/research-first-dev/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/a5c-ai/babysitter/research-first-dev"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/research-first-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00026 | $0.00441 |
| Opus 5 | $0.00013 | $0.00220 |
| Sonnet 5 | $0.00005 | $0.00088 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
research-first-dev 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 9d 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
- Parse the request into specific technical requirements
- Identify the domain and relevant technology stack
- List known constraints (time, resources, compatibility)
- Define success criteria
2. Existing Solution Search
- Search GitHub for similar implementations
- Check package registries (npm, PyPI, crates.io, etc.)
- Review documentation for framework-specific solutions
- Identify relevant design patterns
- Check for known anti-patterns to avoid
3. Alternative Brainstorming
- Generate at least 3 alternative approaches
- Include a "build" option and at least one "buy/reuse" option
- Consider unconventional approaches
4. Trade-Off Evaluation
- Complexity: implementation effort, learning curve
- Time: development timeline, time-to-value
- Risk: failure modes, dependency risks, maintenance burden
- Scalability: growth limits, performance under load
- Score each alternative on all 4 axes
5. Recommendation
- Rank alternatives by composite score
- Provide clear recommendation with justification
- Include risk mitigation plan for chosen approach
- Define go/no-go criteria
Iterative Retrieval
- Start broad, narrow based on findings
- Use confidence scoring to decide when to stop
- Maximum 3 retrieval rounds per topic
- Cache findings for reuse in subsequent phases
When to Use
- New feature development (always)
- Architecture changes
- Technology selection
- Dependency evaluation
- Performance optimization strategy
Agents Used
planner(primary consumer)architect(architecture-specific research)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 61 lines · 26 tokens per session scan A b7ac250f8fdd
research-first-dev is a skill published in the GitHub repository a5c-ai/babysitter (1,788 stars, last pushed 7d ago), licensed MIT. It adds 26 tokens to every session and 441 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
tutti-agent-workspace-app
Build or evolve a complex agent-enabled Tutti workspace app repository. Use for Tutti apps with web/server/shared monorepos, @tutti-os/agent-acp-kit local agent runtimes, kit-owned TUTTICLI agent/composer discovery, dynamic agent catalogs, run-scoped MCP tool gateways, app-owned package builders, web-first debugging…
goga-review-plan
Verify execution plan completeness and correctness.
goga-brainstorm
Pipeline orchestrator for brainstorming the cells architecture.
goga-define-challenge
Challenge the complete product definition before the PRD is generated.
goga-define-experience
Define the user experience required to achieve the established product goals and solve the identified problem.
goga-define-goals
Define the product outcomes that should be achieved by solving the identified problem for the relevant users.