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 Wibias/github-delivery --skill babysitgit clone --depth 1 https://github.com/Wibias/github-deliveryWrote 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/wibias/github-delivery/babysit)<a href="https://agentmods.dev/skills/wibias/github-delivery/babysit"><img src="https://agentmods.dev/badge/skills/wibias/github-delivery/babysit/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/wibias/github-delivery/babysit"><img src="https://agentmods.dev/badge/skills/wibias/github-delivery/babysit.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00040 | $0.00398 |
| Opus 5.5 | $0.00016 | $0.00159 |
| Sonnet 5.5 | $0.00008 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
babysit 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 1mo 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
Babysit → github-delivery
Cursor’s built-in babysit (~/.cursor/skills-cursor/babysit) is a thin
conflict/CI stub. It reinstalls when deleted. Do not follow it when this
personal skill or github-delivery is available.
Do this instead
-
Load skill
github-delivery(usually~/.agents/skills/github-deliveryor~/.cursor/skills/github-delivery). -
Load
github-deliverySKILL.md. Classification:reuse— this alias reuses github-delivery rather than competing with it. Then load the matching workflow (policy modules are declared there):- Default for babysit/watch/monitor →
references/watch-pr.md - If they asked merge-ready →
references/fix-pr-bots.md
- Default for babysit/watch/monitor →
-
First command every wake (watch):
node "<github-delivery>/scripts/watch-wake-gate.mjs" OWNER/REPO NExit
1→ triage OWNER/MEMBER comments in code (rebase/drop overlap / keep leftovers); resolve DIRTY conflicts. ACK-only does not clear. Never report waiting on CI/CodeRabbit while exit1. -
Ordering: reviews/owners → tip update → CI. Never merge-
dev-then-idle.
Do not
- Follow only the built-in babysit steps (conflicts / CI / Bugbot stub).
- Say “up to date with dev; waiting on windows-latest and CodeRabbit” while wake-gate fails.
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.
- 1mo ago Changed 408e352800c1
- 1mo ago Changed · -2 lines · -58 tokens per session 46c31a21ac58
- 2mo ago First seen · 36 lines · 98 tokens per session scan A 79f26e3ddb98
babysit is a skill published in the GitHub repository Wibias/github-delivery (5 stars, last pushed 11d ago), licensed MIT. It adds 40 tokens to every session and 398 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…