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 pr-updategit 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/pr-update)<a href="https://agentmods.dev/skills/outthislife/brooklyn-skills/pr-update"><img src="https://agentmods.dev/badge/skills/outthislife/brooklyn-skills/pr-update/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/pr-update"><img src="https://agentmods.dev/badge/skills/outthislife/brooklyn-skills/pr-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 69 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00068 | $0.01263 |
| Opus 5 | $0.00034 | $0.00632 |
| Sonnet 5 | $0.00014 | $0.00253 |
| Haiku 4.5 | $0.00007 | $0.00126 |
Grade A, and why
pr-update 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Update (open or refresh)
One skill for create and update. Make the title + body match the branch as it is now. Do not strip media from an existing description.
Steps
git status/git diff/git log/git diff <default>...HEAD(and remote tracking) so you know the full change set — not just the latest commit.- Detect an existing PR/MR for this branch (
gh pr view/glab mr view).- None → create (push upstream with
-uif needed). - Exists → edit title + body in place. Do not open a duplicate.
- None → create (push upstream with
- Draft a title and body from all commits/files in the PR, not one commit.
- If updating: fetch the current body first. Preserve every media item exactly (see below). Then rewrite text so Summary / Test plan (or the repo's usual sections) stay accurate.
- Apply with
gh pr create/gh pr edit(orglabequivalents). - End with the PR/MR as a markdown link — the number and the full forge
URL (
[#123](https://github.com/org/repo/pull/123), GitLab!equivalent). Never a bare#123. This is the one place the rule is written down; the other skills just follow it.
Title + body
- Title: concise, why-focused; match repo PR style when obvious.
- Body: use the repo's template when one exists; otherwise:
## Summary
<1-3 bullets of what changed and why>
## Test plan
- [ ] <concrete checks>
- Run the prose through
no-tropesbefore publishing. - Do not invent reviewers, labels, or milestone unless asked.
Commits
Shape the branch's commits as part of opening/refreshing the PR.
- One concern per commit. Default to a topical split (2–5 is typical) even if not asked; don't dump everything into one blob unless the user wants it.
- Match the repo's recent commit style (
git log --oneline -15); subject = why. No "WIP" / "fix stuff". - Rebuild with soft reset + path-staged commits (no
git rebase -i— needs a TTY). Show the finalgit log --oneline <default>..HEADbefore force-push. Two traps in that recipe:- Soft-reset to the branch's real base SHA (
git merge-base HEAD origin/<default>), never toorigin/<default>itself — it moves mid-task and will stage other people's commits as yours. git reset <base> -- <path>leaves that path unstaged, so the nextgit commitsilently captures its pre-edit version. Verify the content landed (git show <sha>:<path> | grep <new symbol>) before force-push.
- Soft-reset to the branch's real base SHA (
- Keep authorship when reshaping others' work (
Co-authored-by/ cherry-pick), especially duringpr-triagesalvage. - Don't mix pure formatting with logic, commit secrets/
.env, or rewrite commits already on the default branch without asking.
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 · 125 lines · 68 tokens per session scan A ee7fa2fb9b66
pr-update is a skill published in the GitHub repository OutThisLife/brooklyn-skills (191 stars, last pushed 23d ago), licensed MIT. It adds 68 tokens to every session and 1,263 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 2026-08-30.
Other skills, from other repositories
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.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.