What is auto_task.restack?

A Git workflow for passing reviewed changes through a stack of dependent pull requests. A pull request is a proposed code change for review; a stacked set means each branch builds on the previous one.

Use it after changing a pull request in the middle or bottom of an existing stack, so later pull requests receive those changes.

It carries fixes from an earlier pull request into later dependent branches without rewriting history or force-pushing. It aims to leave each pull request mergeable with continuous integration checks passing.

How causify-ai/helpers configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to causify-ai/helpers. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/causify-ai/helpers/master/.claude/skills/auto_task.restack/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/causify-ai/helpers

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/causify-ai/helpers/auto_task.restack/github.svg)](https://agentmods.dev/skills/causify-ai/helpers/auto_task.restack)

Your own site

<a href="https://agentmods.dev/skills/causify-ai/helpers/auto_task.restack"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/auto_task.restack/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/causify-ai/helpers/auto_task.restack"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/auto_task.restack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,781 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00015	$0.01781
Opus 5.5	$0.00006	$0.00712
Sonnet 5.5	$0.00003	$0.00356
Haiku 4.5	$0.00002	$0.00178

Measured 29d ago against content hash 26bce7038421, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auto_task.restack 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 29d 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.

.claude/skills/auto_task.restack/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal

Given the current PR is one branch in an existing stack of sequential PRs, each based on the previous one's branch, propagate the changes reviewed/modified in an earlier PR down into every PR stacked on top of it
Preserve full history: propagate by merging forward and committing, never by rebasing or force-pushing
End with every PR in the stack mergeable, with CI green

When to Use This Skill

Use after a PR in the middle (or bottom) of an existing stack was reviewed and changed (e.g. review feedback addressed), and the branches stacked on top of it now need those changes
Do not use this to build a new stack from scratch: use /auto_task.execute_with_stacked_prs for that
Follow .claude/skills/auto_task.rules.md section "Ask for Clarification Before Executing an Unclear Plan" whenever a PR's description does not make clear what it is meant to do: do not guess and merge blind

Workflow

Discover the Full Stack

Get the current PR:

> gh pr view --json number,title,baseRefName,headRefName,url

Walk upward from the current PR's baseRefName, following each branch's own PR (gh pr list --head <base> --state all), until reaching the repo's default branch (master), to find the bottom of the stack
Walk downward from the current PR's headRefName, repeatedly finding the open PR whose baseRefName equals the previous PR's headRefName (gh pr list --base <branch> --state open), to find the top of the stack
Order the discovered PRs bottom (based on master) to top
Check whether the bottom PR itself is behind the default branch:
```
> gh pr view <bottom PR> --json mergeable,mergeStateStatus
```
If mergeable is CONFLICTING (or the branch is simply behind), treat the default branch as an implicit PR_0 at the bottom of the stack: it needs the same merge-forward treatment as every other pair before the rest of the stack can end up mergeable

Print the Stack

Print one table with columns #, Branch, PR (#<NUM> — <title>), Base, e.g.:

+---+--------------------+-----------------------------------------------+--------+
| # | Branch             | PR                                             | Base   |
+---+--------------------+-----------------------------------------------+--------+
| 1 | ..._invoke_tasks   | #1423 -- auto-pick suffix in git_branch_create | master |
| 2 | ..._invoke_tasks_2 | #1424 -- unit tests for git_*/gh_* tasks       | #1423  |
+---+--------------------+-----------------------------------------------+--------+

Read the full file on GitHub · 157 lines

Changes

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.

29d ago First seen · 157 lines · 15 tokens per session scan A 26bce7038421

Subscribe to this mod's changes

auto_task.restack is a skill published in the GitHub repository causify-ai/helpers (150 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 1,781 once invoked, about $0.0001 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 2026-09-18.

Git and workflow

helpers: Skill for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Goal

When to Use This Skill

Workflow

Discover the Full Stack

Print the Stack

What this file has done since we first saw it

Other skills, from other repositories

prowler-commit

gh-auth-isolation

comet-github

release-helper

github-skill

merge-pr