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_remotely_with_single_pr/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_remotely_with_single_pr)<a href="https://agentmods.dev/skills/causify-ai/helpers/auto_task.execute_remotely_with_single_pr"><img src="https://agentmods.dev/badge/skills/causify-ai/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.
<a href="https://agentmods.dev/skills/causify-ai/helpers/auto_task.execute_remotely_with_single_pr"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/auto_task.execute_remotely_with_single_pr.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 | $0.00014 | $0.01580 |
| Opus 5.5 | $0.00006 | $0.00632 |
| Sonnet 5.5 | $0.00003 | $0.00316 |
| Haiku 4.5 | $0.00001 | $0.00158 |
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 16d 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 — 170 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 (theclaude-code-actionGitHub Action), instead of implementing it in this session - The task becomes its own GitHub issue, branch, and draft PR, so the remote run is independent and proceed asynchronously, without a local checkout doing the work
- A task's whole spec lands in a single PR: Claude on GitHub may push multiple commits for different parts of the spec, but must never open a second PR for the same task
- Follow
.claude/skills/auto_task.rules.mdfor how tasks are queued, specified, and named before they reach this skill
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 specified clearly enough to hand to an unattended agent and do not need local interactivity, a local Docker container, or hands-on debugging
- Prefer
.claude/skills/auto_task.execute_interactively/SKILL.mdwhen tasks are exploratory or need a tight local feedback loop between runs - Prefer
.claude/skills/auto_task.execute_with_stacked_prs/SKILL.mdwhen tasks form a real dependency chain and must be branched from each other, not run independently - 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 let a remote run build on top of a guess
Conventions
- Follow
.claude/skills/auto_task.rules.mdfor queue, spec, naming, and coding/testing conventions: they apply to whatever code Claude on GitHub writes, even though it runs remotely and not in this session - Claude on GitHub only starts on an explicit
@claudemention in an issue's title or body, or in a comment on an issue or PR, perhelpers_root/.github/workflows/claude.yml- Assigning the GH issue (
--gh_assignee) does not by itself trigger a run
- Assigning the GH issue (
Constraints
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.
- 16d ago Changed ce94b4df8247
- 29d ago Changed · +8 lines b3552e609c46
- 1mo ago First seen · 162 lines · 14 tokens per session scan A 9b1835e62980
auto_task.execute_remotely_with_single_pr is a skill published in the GitHub repository causify-ai/helpers (150 stars, last pushed today), licensed Apache-2.0. It adds 14 tokens to every session and 1,580 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 2026-09-14.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
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.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.