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 AndrewDongminYoo/cc-agents-kit --skill ci-babysitgit clone --depth 1 https://github.com/AndrewDongminYoo/cc-agents-kitWrote 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/andrewdongminyoo/cc-agents-kit/ci-babysit)<a href="https://agentmods.dev/skills/andrewdongminyoo/cc-agents-kit/ci-babysit"><img src="https://agentmods.dev/badge/skills/andrewdongminyoo/cc-agents-kit/ci-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/andrewdongminyoo/cc-agents-kit/ci-babysit"><img src="https://agentmods.dev/badge/skills/andrewdongminyoo/cc-agents-kit/ci-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 | $0.00064 | $0.02775 |
| Opus 5 | $0.00032 | $0.01388 |
| Sonnet 5 | $0.00013 | $0.00555 |
| Haiku 4.5 | $0.00006 | $0.00278 |
Grade A, and why
ci-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 5d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI Babysit
Watch CI after a push until every job reaches a terminal state. Keep watch-only work read-only. Repair mechanical failures only when the current request or an approved plan gives explicit authority for local repair.
When to use
- Right after
git push,/ship, or/commit-push-pron a branch whose CI result gates the next step, such as merge, release, or a review request. - When the user asks to watch or monitor CI.
- When the user explicitly asks to make CI green or approves a plan that includes local repair.
Do NOT use for: local test runs (just run them), or repos without CI configured.
Authority modes
Watch-only
A request to watch, monitor, or report CI is watch-only unless the same request or an approved plan explicitly authorizes changes. A watch-only request must not rerun jobs, install dependencies, format files, regenerate files, commit, or push. Read check state and logs, then report terminal failures without changing local or remote state.
Make-green
A make-green request must explicitly authorize state-changing reruns or local repair in the current request or an approved plan. Authority to rerun does not authorize local repair. Authority to repair does not authorize a commit or push. Require separate explicit authority for each commit and each push.
Workflow
1. Identify what to watch
branch_name=$(git branch --show-current)
head_sha=$(git rev-parse HEAD)
if ! pr_json=$(gh pr list --head "$branch_name" --state open --limit 2 --json number); then
echo "Active pull-request lookup failed." >&2
exit 1
fi
if ! jq -e 'type == "array" and all(.[]; type == "object" and (.number | type == "number"))' <<<"$pr_json" >/dev/null; then
echo "Active pull-request lookup returned malformed JSON." >&2
exit 1
fi
if [ "$(jq 'length' <<<"$pr_json")" -gt 1 ]; then
echo "Active pull-request lookup returned more than one pull request." >&2
exit 1
fi
pr_number=$(jq -r '.[0].number // empty' <<<"$pr_json")
if [ -n "$pr_number" ]; then
gh pr checks "$pr_number"
else
gh run list --branch "$branch_name" --commit "$head_sha" --limit 100
fi
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.
- 5d ago Changed · +5 lines 92b92f10e37a
- 9d ago First seen · 214 lines · 64 tokens per session scan A 0e917ff71cd1
ci-babysit is a skill published in the GitHub repository AndrewDongminYoo/cc-agents-kit (2 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 2,775 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
cloudflare-workers-testing
Comprehensive testing guide for Cloudflare Workers using Vitest and @cloudflare/vitest-pool-workers. Use for test setup, binding mocks (D1/KV/R2/DO), integration tests, or encountering test failures, mock errors, coverage issues.
cloudflare-workers-ci-cd
Complete CI/CD guide for Cloudflare Workers using GitHub Actions and GitLab CI. Use for automated testing, deployment pipelines, preview environments, secrets management, or encountering deployment failures, workflow errors, environment configuration issues.
bun-sveltekit
Use when building or running SvelteKit apps on Bun, including SSR, adapters, and Bun-specific APIs.
app-store-deployment
Publishes mobile applications to iOS App Store and Google Play with code signing, versioning, and CI/CD automation. Use when preparing app releases, configuring signing certificates, or setting up automated deployment pipelines.
watch-patterns
Correct construction of watchers for long-running operations. TRIGGER when: arming observation of a long-running operation (CI run, deploy, transfer, GC/prune, log stream), writing poll/until loops, or using the Monitor tool. SKIP: defining production alerts/metrics (use monitoring-observability); log formatting (use…
scheduler
Manage scheduled jobs — create, update, list, run remote agents on cron. Use when setting up recurring tasks, checking job status, or managing automation.