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 OutThisLife/brooklyn-skills --skill stacked-prgit clone --depth 1 https://github.com/OutThisLife/brooklyn-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/outthislife/brooklyn-skills/stacked-pr)<a href="https://agentmods.dev/skills/outthislife/brooklyn-skills/stacked-pr"><img src="https://agentmods.dev/badge/skills/outthislife/brooklyn-skills/stacked-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/outthislife/brooklyn-skills/stacked-pr"><img src="https://agentmods.dev/badge/skills/outthislife/brooklyn-skills/stacked-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00047 | $0.00675 |
| Opus 5.5 | $0.00019 | $0.00270 |
| Sonnet 5.5 | $0.00009 | $0.00135 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
stacked-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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stacked & Multi-base PRs
Stacked (dependent) PRs
A child PR builds on a parent PR's branch. Update the stack bottom-up:
- Update the parent branch/PR first.
- Rebase the child onto the updated parent — not onto the default branch, and never "merge main into the leaf" as the only step.
- Push each level; keep each PR's base pointing at the one below it.
Multi-base (release + default)
Some orgs require the same change on the default branch AND a release/production branch:
- Confirm the required target branches from the repo's rules.
- Land the change once, then cherry-pick/port the identical code to the other base as a second PR.
- Keep the two PRs' code identical; note the sibling in each description.
- Treat the duplicate as a fresh review target. Request the original developer reviewer/team and use the repo's pending human/code-review labels. Do not copy QA approval or claim a developer checkmark from the sibling; the release PR needs its own explicit developer approval. Verify assignees, review requests, and labels after updating them.
Estimate an integration before changing branches
- Fetch the real upstream default branch and every dependency head; compare ancestry so already-included fixes are not imported twice.
- Use
git merge-tree --write-tree --name-only <base> <head>to estimate conflicts without modifying a checkout or index. Report conflict counts as textual integration scope, not proof that auto-merged code is correct. - Preserve current upstream security and profile-routing behavior when reconciling older UI work; do not resolve whole files with ours/theirs just to eliminate markers.
- Distinguish updating the local clone from publishing a fork-default update. A PR in a separate repository still compares against that repository's base; local upstream freshness does not update it.
MR additive-repair safeguards
- Invoke the pinned Node executable directly for worktree tests and set
NODE_PATHto that worktree'smr_moduleson the command. Shared dependency symlinks and concurrent shells can otherwise resolve another checkout; verifyprocess.execPathandrequire.resolve('MRUtils')first. - Check the merge commit's effective diff against its own base, not only HEAD. Lint-staged sees upstream files staged by a merge and can rewrite unrelated code; run targeted lint/tests and use a per-invocation hook override for the additive merge commit rather than changing repository hook configuration.
- Reconcile CMS migration composition with already-merged migrations in both execution orders. Preserve foreign-edit/staged-batch refusal and verify published records before retiring an old route; saved redirect flags alone do not establish that a redirect reached production.
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 Changed · +18 lines 25239c452c08
- 2mo ago First seen · 35 lines · 47 tokens per session scan A 378e9159694a
stacked-pr is a skill published in the GitHub repository OutThisLife/brooklyn-skills (209 stars, last pushed 7d ago), licensed MIT. It adds 47 tokens to every session and 675 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
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.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.