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 agentmods add skills/cleverbrush/xpenser/pr-workflownpx skills add cleverbrush/xpenser --skill pr-workflowgit clone --depth 1 https://github.com/cleverbrush/xpenserWhat 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 | $0.00060 | $0.01762 |
| Opus 5 | $0.00030 | $0.00881 |
| Sonnet 5 | $0.00012 | $0.00352 |
| Haiku 4.5 | $0.00006 | $0.00176 |
Grade A, and why
pr-workflow 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 2d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Workflow
Follow this workflow whenever PR work is expected to ship through a pull request.
Project Guide
- First read
.agents/pr-workflow.mdin the repository root when it exists. - Treat that file as the source of truth for project-specific details: GitHub repository, default branch, validation commands, required checks, preview URL rules, preview credentials, telemetry filters, and notification project name.
- If the project guide is missing, discover the same facts from the repo, CI config, package manifests, and PR metadata. Ask the user only when a required project-specific fact cannot be discovered safely.
Worktree Setup
- Never implement PR work directly on
mainormaster. - Start by checking
git status --short --branchin the current checkout and preserve unrelated user changes. - Classify the task before creating the branch:
- Use
feat/<task-slug>for new functionality or behavior expansion. - Use
fix/<task-slug>for bug fixes or regressions.
- Use
- Create the dedicated worktree next to the
maincheckout, under the same root directory:- Main checkout:
<root>/main - Feature worktree:
<root>/feat/<task-slug> - Bug-fix worktree:
<root>/fix/<task-slug>
- Main checkout:
- Use the selected branch name and matching sibling worktree path, for example:
mkdir -p ../<branch-type>
git fetch origin main
git worktree add -b <branch-type>/<task-slug> ../<branch-type>/<task-slug> origin/main
- Do all implementation, local verification, commits, and pushes from the worktree.
- If a worktree or branch already exists for the task, inspect it and continue there instead of creating a conflicting branch.
Local Implementation
- Follow the repo conventions and the validation commands listed in
.agents/pr-workflow.md. - Add or update focused unit tests for changed logic when applicable.
- Add or update e2e tests for changed user-facing flows when applicable. Use the project guide for required base URLs, credentials, and setup helpers.
Feature Blog Post
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.
- 2d ago First seen · 102 lines · 60 tokens per session scan A 91f4723a218e
pr-workflow is a skill published in the GitHub repository cleverbrush/xpenser (5 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,762 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
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
teamharness-task-delegation
Use when a Leader turns ready Quick Task or Project Work state into Worker task instructions, sends assignment messages, checks submitted results, and defines completion/blocker report contracts. Do not use to create projects, create rooms, or execute Worker tasks.
dot-ai-prd-create
Create documentation-first PRDs that guide development through user-facing content.
agent-upkeep
Perform one small, scoped maintenance improvement to the Elements monorepo and open a single reviewable pull request. Use this skill for scheduled or unattended upkeep runs that improve unit test coverage for one file, fix one behavioral bug in one module, or move one off ESLint rule toward enforcement to reduce…
bmad-check-implementation-readiness
Validate PRD, UX, Architecture and Epics specs are complete. Use when the user says "check implementation readiness".