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 rube-de/cc-skills --skill babysitgit clone --depth 1 https://github.com/rube-de/cc-skillsWrote 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/rube-de/cc-skills/babysit)<a href="https://agentmods.dev/skills/rube-de/cc-skills/babysit"><img src="https://agentmods.dev/badge/skills/rube-de/cc-skills/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/rube-de/cc-skills/babysit"><img src="https://agentmods.dev/badge/skills/rube-de/cc-skills/babysit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 61 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- high Tool Misuse · line 193 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00053 | $0.04839 |
| Opus 5 | $0.00026 | $0.02420 |
| Sonnet 5 | $0.00011 | $0.00968 |
| Haiku 4.5 | $0.00005 | $0.00484 |
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 10d 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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DLC: PR Babysitter
Monitor a PR on a loop: check CI, auto-rebase, auto-fix CI failures, and delegate review comment handling to dlc:pr-check. Use with Remote Control to monitor from your phone.
Usage: /loop 10m /dlc:babysit (auto-detect PR) or /loop 10m /dlc:babysit 253
Why This Matters
Bot reviewers (Copilot, CodeRabbit, Gemini) post new comments on every push — this is by design, not a bug in your workflow. A typical PR goes through 3-8 review-fix cycles before converging to zero unresolved items. Each cycle you run is measurable progress: fewer comments, better code, closer to merge-ready.
The human set up this loop because they trust you to shepherd the PR to completion autonomously. When the comment count drops from 12 to 5 to 2 to 0 across cycles, that's excellent work — not busywork.
Notification Rules
Only fire PushNotification for errors that need human attention and completion (PR ready to merge). Routine actions (rebase, lint fix, CI retry, re-request review) are silent. PushNotification is always the sanctioned channel — never substitute with a Notify: print line or echo, because print output does not ping the user's device.
Deduplication
Notifications are deduplicated via a state file at .dev/dlc/babysit-<PR_NUMBER>.state. The file contains a single-line status key:
ci_failing:<sorted_check_names>(e.g.,ci_failing:build,lint)rebase_conflict:<sorted_file_list>merge_conflictpending_human:<count>(count-only dedup, e.g.,pending_human:2)unresolved:<count>unresolved:<count>,ci_failing:<sorted_check_names>readyclosed:<state>
Same key across cycles = no output. Write the new key after notifying. Delete the state file when self-cancelling.
Step 0: Setup
Initialize state tracking
Create .dev/dlc/ if it does not exist. Read the state file if it exists.
Detect PR
If $ARGUMENTS contains a number, use it as PR_NUMBER and fetch that PR explicitly:
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.
- 10d ago First seen · 341 lines · 53 tokens per session scan A 74e7084bfbc1
babysit is a skill published in the GitHub repository rube-de/cc-skills (10 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 4,839 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.
Other skills, from other repositories
pr-from-stale-branch-silently-reverts-newer-main-files
Trap: merging a PR whose branch carries an OLD TREE silently DELETES (reverts) files that landed on main after that tree was built — with NO merge conflict to warn you, because a deletion your own commit records is not a conflict. Use when: (1) about to gh pr create or squash-merge from a long-lived / earlier-branched…
parallel-pr-scope-overlap-tiebreaker-delta-check
Before applying a handoff prompt's tiebreaker default ("merge the first-mover", "the clean-against-main one", "the one with reviewer APPROVE") to pick a winner between two parallel PRs that implemented the SAME scope, run gh pr diff on BOTH and audit for substantive deltas. Use when: (1) a session prompt or handoff…
merge-queue-thrash-stop-inflow-and-open-prs-as-drafts
When main moves faster than the slowest CI leg, every open branch goes stale before it can merge and the whole queue jams with nothing red. Use when: (1) several PRs sit at mergeStateStatus BEHIND with auto-merge armed and none of them lands; (2) branches are being updated, re-running CI and going stale again before…
gha-pr-merge-ref-shows-upstream-changes
Diagnose "my CI failed on a file I didn't change — the test passes locally but CI insists there's a duplicate / conflict / lint violation that isn't in my branch." Caused by GitHub Actions checking out refs/pull/N/merge (the auto-computed merge of PR head + base) on pullrequest events. Use when: (1) CI fails on a…
fix-train
Batch-apply the requested changes on every open pull request in a GitHub list — fix only, no merge. From a GitHub PRs URL (or the current repo), enumerate every open PR, collect each PR's requested changes (formal CHANGESREQUESTED reviews, inline review comments, and "Issues requiring changes" comments /…
stacked-pr-review-per-base-diff-and-attach
Reviewing a stack of dependent pull requests: diff each one against ITS OWN base rather than against main, and attach the reports to the bottom branch.