What is auto_task.execute_remotely_with_single_pr?

A workflow that sends a specified task to Claude running in GitHub through the Claude Code Action, creating one issue, branch, and draft pull request for the task. It performs the work remotely rather than in the local checkout.

Use it to delegate well-defined coding tasks that do not need local Docker, interactive decisions, or a tight debugging loop.

It lets a clear, unattended task run asynchronously without local implementation or hands-on debugging.

auto_task.execute_remotely_with_single_pr — Skill by gpsaggese/helpers

Install

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.

Any agent

npx skills add gpsaggese/helpers --skill auto_task.execute_remotely_with_single_pr

Clone the repo

git clone --depth 1 https://github.com/gpsaggese/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/gpsaggese/helpers/auto_task.execute_remotely_with_single_pr/github.svg)](https://agentmods.dev/skills/gpsaggese/helpers/auto_task.execute_remotely_with_single_pr)

Your own site

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

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,469 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	$0.00014	$0.01469
Opus 5.5	$0.00006	$0.00588
Sonnet 5.5	$0.00003	$0.00294
Haiku 4.5	$0.00001	$0.00147

Measured yesterday against content hash 9073e12f547b, 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.execute_remotely_with_single_pr 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 yesterday.

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.execute_remotely_with_single_pr/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal

Execute a well-specified task <FILE> by delegating it to Claude running remotely on GitHub (the claude-code-action GitHub Action), not by implementing it in this session
The task becomes its own GitHub issue, branch, and draft PR, so the remote run is independent and asynchronous, with no local checkout doing the work
A task's whole spec lands in one PR: Claude on GitHub may push several commits for different parts, but must never open a second PR for the same task
Follow .claude/skills/auto_task.rules.md for how tasks are queued, specified, and named

Inputs

<FILE> or a GitHub issue already filed (e.g., #580 or https://github.com/gpsaggese/gpsaggese.github.io/issues/580)

When to Use This Skill

Use it when tasks are clear enough for an unattended agent, and need no local interactivity, local Docker container, or hands-on debugging
Prefer .claude/skills/auto_task.execute_interactively/SKILL.md for exploratory tasks or a tight local feedback loop
Prefer .claude/skills/auto_task.execute_with_stacked_prs/SKILL.md for a real dependency chain that must be branched from each other
Follow .claude/skills/auto_task.rules.md section "Ask for Clarification Before Executing an Unclear Plan" when the spec is unclear or incomplete: a remote run must not build on a guess

Conventions

Follow .claude/skills/auto_task.rules.md for queue, spec, naming, and coding/testing conventions. They apply to the code Claude on GitHub writes
Claude on GitHub starts only on an explicit @claude mention in an issue's title or body, or in an issue or PR comment, per helpers_root/.github/workflows/claude.yml
- Assigning the GH issue (--gh_assignee) does not trigger a run

Constraints

Do not implement a task's code yourself: dispatch it, then only monitor and report on the run and PR
Do not commit, push, or amend the task's branch: Claude on GitHub pushes to it, and merging is the user's decision
Keep one PR per task: several commits on that PR are fine, but never open a second issue/branch/PR for a dispatched task

Read the full file on GitHub · 163 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.

yesterday First seen · 163 lines · 14 tokens per session scan A 9073e12f547b

Subscribe to this mod's changes

auto_task.execute_remotely_with_single_pr is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 14 tokens to every session and 1,469 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 2026-11-06.

Building agents Git and workflow

auto_task.execute_remotely_with_single_pr next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
auto_task.execute_remotely_with_single_prgpsaggese/helpers	Skill	158	today	Apache-2.0	A	14	Claude Code
merge-batchdiegosouzapw/OmniRoute	Skill	83k	6d ago	MIT	A	46	Claude Code
prowler-commitprowler-cloud/prowler	Skill	15k	today	Apache-2.0	A	44	Claude Code, Codex
gh-auth-isolationgithub/gh-aw	Skill	5.6k	today	MIT	A	20	Claude Code, Codex
comet-githubrpamis/comet	Skill	3.3k	yesterday	MIT	A	72	Claude Code, Codex
github-skillzeenie-ai/OpenCompany	Skill	1.1k	2d ago	MIT	A	51	Claude Code
release-helperSahir619/fable-method	Skill	2.3k	1mo ago	MIT	A	43	Claude Code