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.
curl -O https://raw.githubusercontent.com/causify-ai/helpers/master/.claude/skills/auto_task.execute_with_stacked_prs/SKILL.mdgit clone --depth 1 https://github.com/causify-ai/helpersWrote 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/causify-ai/helpers/auto_task.execute_with_stacked_prs)<a href="https://agentmods.dev/skills/causify-ai/helpers/auto_task.execute_with_stacked_prs"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/auto_task.execute_with_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/causify-ai/helpers/auto_task.execute_with_stacked_prs"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/auto_task.execute_with_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 | $0.00013 | $0.01866 |
| Opus 5.5 | $0.00005 | $0.00746 |
| Sonnet 5.5 | $0.00003 | $0.00373 |
| Haiku 4.5 | $0.00001 | $0.00187 |
Grade A, and why
auto_task.execute_with_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 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.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
- Execute one GitHub issue as a stack of sequential branches and PRs, each named
<BASE>_<ID>(ID= 1, 2, 3, ...) and each branched from the previous one, so the PRs stack in review order - Create the whole stack without stopping for review between branches
- The user then reviews, edits, and merges each PR bottom-up at their own pace, after this skill's job is done
- Follow
.claude/skills/auto_task.rules.mdfor how tasks are queued, specified, and named before they reach this skill
Input
- The user will pass you a task in the format
When to Use This Skill
- Use it only when the tasks favor stacked execution: specs are complete, tasks form a real dependency chain, and the user prefers one batch review over interruptions
- Follow
.claude/skills/auto_task.rules.mdsection "Ask for Clarification Before Executing an Unclear Plan" when a task's spec is unclear or incomplete: do not keep building downstream tasks on top of a guess - Make sure that once you start implementing the stack all the doubts have been clarified by asking to the user, so that you can proceed without interruptions
Workflow
Confirm the Task List
- Follow
.claude/skills/auto_task.rules.mdsection "Confirm the Task List Before Executing" for the task list format and the problem/solution check; these ordered tasks are the stack's branches, one task per branch - Confirm task
<ID+1>depends only on task<ID>, not onmasterand not on an earlier task in the list - If the order or a dependency is unclear, ask before starting: fixing a wrong dependency after the stack is built means rebasing everything above it
Create the Issue and the First Branch (_1)
-
Follow
.claude/skills/auto_task.rules.mdsection "One GitHub Issue Is the Unit of Work": one GH issue covers the whole stack, not one issue per branch -
Create the issue and the first branch / PR
<BASE>_1> git_create_issue_and_branch.py \ --gh_issue_title "<TITLE>" --gh_issue_body "<Description of entire stack>" \ --suffix 1
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 Changed · +12 lines f1860c1a8c64
- 1mo ago Changed · -13 lines 887712bcd620
- 1mo ago Changed d32cd8463f59
- 1mo ago First seen · 162 lines · 13 tokens per session scan A 2241525cc2e4
auto_task.execute_with_stacked_prs is a skill published in the GitHub repository causify-ai/helpers (150 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 1,866 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 2026-09-08.
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.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.
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.
merge-pr
Merge a pull request with status checks, squash merge, and branch cleanup. Handles worktree contexts.