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/bendrucker/claude/stacknpx skills add bendrucker/claude --skill stackgit clone --depth 1 https://github.com/bendrucker/claudeWhat 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 | $0.00070 | $0.02155 |
| Opus 5 | $0.00035 | $0.01077 |
| Sonnet 5 | $0.00014 | $0.00431 |
| Haiku 4.5 | $0.00007 | $0.00215 |
Grade A, and why
github:stack 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stacked Pull Requests
gh stack (the github/gh-stack extension) drives GitHub's native stacked PRs. The stack object on GitHub is the same either way, and so is the merge. What differs is where the branches live locally, which decides how the stack gets built and published.
Layouts
Native tracking keeps every layer checked out in one working tree. gh stack owns the branches, the rebases, and the publish. This is what the extension is built for, and it gets the interactive PR editor, cascading rebase, and one-command sync.
External tracking keeps each layer somewhere else, typically its own worktree. Another tool owns the rebases and gh stack link publishes the result. link is documented for exactly this and writes no local state.
Pick per stack. The choice can differ across stacks in one repository. Native tracking fits a stack you are actively reshaping, where reordering and folding layers matters more than working two layers at once. External tracking fits a stack whose layers are worked on in parallel or over a long stretch, where each layer wants its own checkout, editor, and running services.
Read the current state with gh stack view --short (add --json to parse it). It answers from local tracking. Output means native tracking, and an error means the stack is not tracked here. That is a statement about this clone, not about GitHub: a stack published by link is real on GitHub and still absent from view.
Don't mix them for one stack. The local-tracking commands silently under-perform against branches they can't check out. gh stack rebase prints ✓ Rebased <branch> and changes nothing when that branch is checked out in a different worktree (gh-stack#35).
Exit code 9 means the repository doesn't have stacked PRs enabled. Code 6 means a branch belongs to more than one stack, or more than one remote is configured with no remote.pushDefault set. link, submit, push, and sync take --remote for that second case.
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 · 110 lines · 70 tokens per session scan A 1dae7d095cfd
github:stack is a skill published in the GitHub repository bendrucker/claude (16 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 2,155 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…