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 hani-q/qstack --skill qstack-babysit-prgit clone --depth 1 https://github.com/hani-q/qstackWrote 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/hani-q/qstack/qstack-babysit-pr)<a href="https://agentmods.dev/skills/hani-q/qstack/qstack-babysit-pr"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-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/hani-q/qstack/qstack-babysit-pr"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-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 | $0.00032 | $0.00609 |
| Opus 5.5 | $0.00013 | $0.00244 |
| Sonnet 5.5 | $0.00006 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
qstack-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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Babysit a PR
Keep one existing pull request current until its required checks and review bots finish on the latest head commit. The user's original goal remains the scope.
Start with the current PR
Resolve the PR from the request or current branch. Record its URL, base branch, head commit, latest push time, required checks, and review state. Confirm the local checkout matches its head before editing. If several PRs fit, ask which one to watch.
Watch and respond
Use an available PR event monitor; otherwise poll for new comments, reviews, checks, and base-branch changes at a reasonable interval while this session is active. After each push, update the head commit and event boundary. Process new events after that push, and confirm earlier actionable threads were actually addressed. A pending check or bot review is still pending, even if other checks are green. Stay quiet when nothing has changed.
For each new finding, read the cited code and surrounding behavior before editing. Fix a real defect within the PR's original goal and verify the fix. Investigate failed checks far enough to distinguish a repository failure from an infrastructure flake; rerun a flake when the host supports it. For an incorrect or out-of-scope finding, reply with the concrete reason and resolve the thread when appropriate. Identify an agent-authored reply as such when it is posted through a person's account. Use the host's comment skill if one is available. Add screenshots or video only when they clarify a specific finding and an upload path is available.
Follow the repository's rules for committing and pushing fixes. Run relevant checks before updating the PR, then watch the new head. Keep up with changes to the base branch; rebase when needed and permitted by the repository workflow. Get explicit authorization before a history rewrite or force push. If another PR makes this one obsolete, stop and explain the overlap. Close it only when the user has authorized closure.
Finish
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 59 lines · 32 tokens per session scan A 5f04970dac98
qstack-babysit-pr is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 609 once invoked, about $0.0001 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 2026-09-23.
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…