Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add bengous/claude-code-plugins/plugin install github-flowWrote 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/bengous/claude-code-plugins/stacked-prs)<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/stacked-prs"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/stacked-prs/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/bengous/claude-code-plugins/stacked-prs"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/stacked-prs.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 | $0.00114 | $0.02905 |
| Opus 5 | $0.00057 | $0.01452 |
| Sonnet 5 | $0.00023 | $0.00581 |
| Haiku 4.5 | $0.00011 | $0.00291 |
Grade A, and why
stacked-prs 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 5d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stacked PRs with gh stack
A stack is a chain of branches above the trunk, one PR per branch, each PR based on the branch below it. Each PR shows only its own diff. Nothing merges before the end: the stack lands in one operation, bottom to top. Local tracking lives in .git/gh-stack (never versioned); the stack object lives on GitHub.
trunk
└── layer-1 PR → trunk
└── layer-2 PR → layer-1
└── … PR → previous layer
The cycle
| Command | Effect |
|---|---|
gh stack init [branches…] [--base <trunk>] |
Creates the stack. Adopts existing branches, bottom to top. |
gh stack add <branch> -m "msg" [-A|-u] |
Branches from the current top and commits what is staged. -A stages everything, untracked included; -u tracked files only. |
gh stack submit [--auto] [--open] |
Pushes everything, creates the missing PRs with the right base, updates existing bases, creates or updates the GitHub stack. |
gh stack push |
Pushes active branches, --force-with-lease branch by branch, not atomic: a rejected branch does not cancel the others. Skips merged and queued branches. Opens no PR. |
gh stack view [--short|--json] |
State: ✓ merged, ◎ queued, ○ open, ⚠ needs rebase. |
gh stack sync [--prune] |
Fetches, reconciles with GitHub, fast-forwards the trunk, cascade-rebases, pushes atomically with --force-with-lease. Creates no PR. |
gh stack rebase [--downstack|--upstack|--no-trunk] |
Cascade rebase: each layer receives the tip of the previous one, after a trunk fetch unless --no-trunk. --continue after conflicts, --abort restores everything. |
gh stack merge [n] [--merge|--squash|--rebase] [--yes] |
Atomic landing, all or nothing, up to the chosen PR. One method for the whole operation, never per PR. --squash squashes each PR into one commit, not the stack into one: three layers land as three commits, each suffixed (#N). --rebase keeps every commit of every layer, in order. With a merge queue, the stack joins the queue and lands when the queue processes it. |
gh stack checkout <n|PR|URL|branch> |
Fetches a stack from GitHub, even one never tracked locally. |
gh stack modify |
TUI: drop, fold, insert, reorder, rename, applied together on confirm. Then submit when PRs are affected. |
gh stack link <n|branch> <branch…> |
Stacks without local tracking; pushes the branches and opens the missing PRs. n first appends to the top of stack n. Two arguments minimum: it cannot create a one-PR stack. |
gh stack unstack [--local] |
Undoes the stack on GitHub, locally, or both. |
up, down, top, bottom, trunk, switch |
Navigation inside the stack. |
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.
- 5d ago First seen · 109 lines · 114 tokens per session scan A b8985f0befc2
stacked-prs is a skill published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 2,905 once invoked, about $0.0006 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 2026-09-12.
Other skills, from other repositories
commit-msg
You receive a git diff of staged changes via stdin. Generate a commit message.
security-pipeline
Use when security verification is needed - pre-commit security checks, vulnerability scanning, STRIDE threat analysis. Integrates with /handoff-verify --security and /commit-push-pr. CWE Top 25 based.
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
git-pushing
Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", "push this", "push to github", or similar git workflow requests.
pr-comment-resolver
Addresses PR review comments by implementing requested changes and reporting resolutions. Use when code review feedback needs to be resolved with code changes.
git-history-analyzer
Performs archaeological analysis of git history to trace code evolution, identify contributors, and understand why code patterns exist. Use when you need historical context for code changes.