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 agentic-dev3o/devx-plugins --skill babysit-prgit clone --depth 1 https://github.com/agentic-dev3o/devx-pluginsWrote 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/agentic-dev3o/devx-plugins/babysit-pr)<a href="https://agentmods.dev/skills/agentic-dev3o/devx-plugins/babysit-pr"><img src="https://agentmods.dev/badge/skills/agentic-dev3o/devx-plugins/babysit-pr/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/agentic-dev3o/devx-plugins/babysit-pr"><img src="https://agentmods.dev/badge/skills/agentic-dev3o/devx-plugins/babysit-pr.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 | $0.00124 | $0.03081 |
| Opus 5.5 | $0.00050 | $0.01232 |
| Sonnet 5.5 | $0.00025 | $0.00616 |
| Haiku 4.5 | $0.00012 | $0.00308 |
Grade A, and why
babysit-pr 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.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Babysit PR
Drive the pull request in $ARGUMENTS (PR number or URL; empty means the PR of the current
branch) to green — every required check passing, no merge conflict — or to a blocker only the
user can clear.
This skill watches, diagnoses, and classifies. It does not own git mutations: commits go
through devx-git:ci, base-branch merges through devx-git:update-origin. Never merge the PR.
Copy this checklist into the reply and keep the counters current — they are the only state that survives between steps:
Babysit PR #<n>:
- [ ] Preflight — PR resolved, head branch checked out, tree clean
- [ ] Watch — exit code dispatched
- [ ] Failures listed by bucket
- [ ] Diagnosed and classified
- [ ] Acted — fix and push, or rerun
- [ ] Mergeable
Budgets: pushes 0/5 · reruns 0/3 · started <HH:MM>, cap 45 min
Attempts: <job> · <error-signature> ×N
Step 1: Preflight
gh auth status
gh pr view $ARGUMENTS --json number,url,state,isDraft,headRefName,headRepositoryOwner,isCrossRepository,baseRefName
git status --porcelain
git branch --show-current
Shell variables do not survive between Bash calls. Record <pr>, <owner>/<repo>,
<head-branch>, and <base-branch> from that output and write the literal values into
every later command. A PR=$(...) set here is empty in the next call, and gh pr checks ""
does not error — it silently falls back to the current branch's PR. Pass -R <owner>/<repo>
to every gh call, or a PR URL argument's repo is discarded.
Stop and report when:
ghis missing or unauthenticated, or no PR resolves (empty output).isCrossRepositoryis true — a fork PR's head branch is not pushable from here.headRefNamediffers from the current branch. Rungh pr checkout <pr> -R <owner>/<repo>, or stop if that would discard work. Without this check, every commit below lands on whatever branch happens to be checked out.git status --porcelainis non-empty.devx-git:cianddevx-git:update-originboth require a clean tree; never stash silently.
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 First seen · 246 lines · 124 tokens per session scan A e84a30247369
babysit-pr is a skill published in the GitHub repository agentic-dev3o/devx-plugins (12 stars, last pushed 10d ago), licensed MIT. It adds 124 tokens to every session and 3,081 once invoked, about $0.0005 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 2026-09-19.
Other skills, from other repositories
repair-github-ci
Fix failing GitHub CI / Actions checks via fixgithubprci and push to the existing PR head, or fix a branch's failing CI via a linked repair worktree.
mcore-create-issue
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
debug-task
Diagnose and fix moon tasks that are broken, misconfigured, or behaving unexpectedly. Use this skill when a moon task is failing, not running, skipped, hanging, producing stale or wrong output, cached when it shouldn't be, re-running every time, or missing outputs after a cache hit. Also covers pipeline hangs, tasks…
operating-github-ci-fixer
Use when the user asks OpenSRE to fix failing GitHub CI, GitHub Actions checks, failing pull request checks, a broken PR branch, or CI on a named branch such as main.
meta-long-running-build-watchdog
Watches a long-running command via tmux, lets sub-agent diagnose failures and propose a fix, and records the diagnosis to memory. Designed for overnight model fine-tunes, CI image builds, or repeated regression suites that may fail intermittently.
gh-fix-ci
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use gh to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.