Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add paulbaranowski/wild-horses/plugin install wild-prWrote 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/commands/paulbaranowski/wild-horses/babysit)<a href="https://agentmods.dev/commands/paulbaranowski/wild-horses/babysit"><img src="https://agentmods.dev/badge/commands/paulbaranowski/wild-horses/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/commands/paulbaranowski/wild-horses/babysit"><img src="https://agentmods.dev/badge/commands/paulbaranowski/wild-horses/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 | $0.00044 | $0.05933 |
| Opus 5 | $0.00022 | $0.02967 |
| Sonnet 5 | $0.00009 | $0.01187 |
| Haiku 4.5 | $0.00004 | $0.00593 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/wild-pr:babysit — watch CI and review feedback
Setup
The user invokes this skill with an optional PR number or URL. Parse in this order and stop at the first match:
- Full PR URL: if the user's text contains
https?://github\.com/[^/\s]+/[^/\s]+/pull/\d+, capture the URL. - Explicit PR token: match
(?:PR|pr|pull request)\s*#?(\d+)or a bare#(\d+)in the user's text. - Bare numeric argument: only when the complete text is a positive integer without surrounding prose.
- None of the above: operate on the PR for the current branch.
All helper logic lives in one CLI, ${CLAUDE_PLUGIN_ROOT:-${CURSOR_PLUGIN_ROOT}}/scripts/pr_babysit_cli.py (or under ${CURSOR_PLUGIN_ROOT}/scripts/ in Cursor), invoked as python3 "<path>" <subcommand>. Subcommands: review, failed-logs, commit-push, reply, comment.
Sentinels
The skill uses two sentinels with visible footer lines.
Addressed sentinel: <sub>🤖 <code>pr-babysit:addressed v1 [email protected]</code></sub>. Appended on its own line at the end of every reply the skill posts so re-runs know which threads and review-body comments are already handled. Dedupe also recognizes legacy cb-babysit:addressed v1 and babysit-pr:addressed v1 prefixes from prior babysit implementations.
Follow-up sentinel: <sub>🤖 <code>pr-babysit:followup v1 [email protected]</code></sub>. Attached to replies that defer an out-of-scope comment as a tracked follow-up. The sentinel is additive: the reply and comment subcommands still append the addressed sentinel at the end.
Sentinel recency rules. The script emits a per-thread activityState with three values. Step 6a owns the handling rules for each state.
active: no sentinel yet, OR at least one human commented after the last sentinel.uncertain: a sentinel exists AND one or more bot comments appeared after it. The thread carries apostSentinelBotCommentsarray listing EVERY such comment.addressed: the sentinel is the newest relevant activity on the thread.
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 · 313 lines · 44 tokens per session scan A 35783e40843f
babysit is a command published in the GitHub repository paulbaranowski/wild-horses (12 stars, last pushed 21d ago), licensed MIT. It adds 44 tokens to every session and 5,933 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
speckit.spex.submit
Push and create PR for team review, with optional watch mode for CI monitoring.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
code-review
Code review for branch changes. Analyzes git diff between branches with multi-level depth (low/medium/high). Matches changes against task description. Returns structured report with severity levels and verdict.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.