babysit-builders

babysit-builders is a skill for Claude Code, Codex from Justinmendezai/The-Adam-Repo. It costs 52 tokens per session (1,741 once invoked), scanned A, original, Apache-2.0.

A monitoring process for coding helpers that are working on separate build tasks. It detects blocked workers, failed tests, unfinished results, out-of-scope file changes, merge conflicts, and tasks stuck in progress.

In plain words
What is it for?
Use it to retry or redirect failed build tasks, collect completed commits, check verification scripts, handle scope violations and merge conflicts, and record human-only follow-up work.
Why use it?
It keeps an automated build moving when a helper fails or needs correction, while sending work that requires a person to a review queue.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions AGENTS.md.

Good fit Use it to retry or redirect failed build tasks, collect completed commits, check verification scripts, handle scope violations and merge conflicts, and record human-only follow-up work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/justinmendezai/the-adam-repo/babysit-builders
Install

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.

Any agent
npx skills add Justinmendezai/The-Adam-Repo --skill babysit-builders
Clone the repo
git clone --depth 1 https://github.com/Justinmendezai/The-Adam-Repo

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for babysit-builders

README.md
[![agentmods](https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/babysit-builders/github.svg)](https://agentmods.dev/skills/justinmendezai/the-adam-repo/babysit-builders)
Your own site
<a href="https://agentmods.dev/skills/justinmendezai/the-adam-repo/babysit-builders"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/babysit-builders/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.

agentmods 80×15 button for babysit-builders

Your own site · 80×15
<a href="https://agentmods.dev/skills/justinmendezai/the-adam-repo/babysit-builders"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/babysit-builders.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,741 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.01741
Opus 5 $0.00026 $0.00870
Sonnet 5 $0.00010 $0.00348
Haiku 4.5 $0.00005 $0.00174

Measured 12d ago against content hash c7a77bdcf591, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

babysit-builders 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 12d 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.

skills/babysit-builders/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

babysit-builders

Builders fail. Builders ask for clarification. Builders sometimes touch paths they shouldn't. This skill keeps them on track autonomously — re-dispatch with fixes, queue human-only work for final review, never stop the loop to ask the operator mid-run.

Triggers

  • Subagent emits <adam>BLOCKED</adam> with a reason.
  • Subagent finishes without the completion signal.
  • Subagent's tests are still red after it claims complete.
  • The Tier-1 orchestrator's independent re-run of slices/<id>/verify.sh exits non-zero even though the worker emitted <adam>COMPLETE</adam> — this is the most common failure mode.
  • Subagent touched a paths_out_of_scope file.
  • Subagent's branch has merge conflicts with main after wave completion.
  • Row stuck in dispatched in agent-control/slice-status.md (manager/worker hung).
  • Worker emitted <adam>CODE-COMPLETE</adam> — queue to human-queue.md; do not pause independent branches.

In the 3-tier topology, you may be triaging the manager's one-line summary rather than the worker's output directly. The manager's full run-result lives at scratch/run-results/<slice-id>.manage.json; the worker's at scratch/run-results/<slice-id>.json. Read those, not the chat scrollback.

Rework ledger (agentic closed loop)

On every auto-retry / focused re-dispatch (and on flip to escalate after the 3rd fail), append one row to agent-control/rework-ledger.md before the follow-up dispatch. Create the file from ~/adam/foundation/repo/agent-control/rework-ledger.md if missing. stage=babysit, pick one class from that file's taxonomy, one_liner = symptom + resolution hint, system_fix=none unless you patch SPEC/CONTEXT/skill this turn. Do not double-count a row already written by review-via-graph / review-runtime for the same event.

Human queue (batched final review)

Append to agent-control/human-queue.md instead of stopping for the operator:

| HQ-NNN | <slice-id> | live-integration | <one line> | <operator_command> | open | |

Read the full file on GitHub · 100 lines

Changes

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.

  1. 12d ago First seen · 100 lines · 52 tokens per session scan A c7a77bdcf591

Subscribe to this mod's changes

babysit-builders is a skill published in the GitHub repository Justinmendezai/The-Adam-Repo (12 stars, last pushed 18d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,741 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens