What is auto_task.execute_interactively?

A workflow skill for carrying out a list of coding tasks one at a time, with an agent review and a human review between tasks. Changes are made in a branch, but the skill does not commit or merge them.

Use it to implement a defined task list, pause when a task needs clarification, run the relevant tests, and prepare changes for the user to commit.

It prevents later tasks from being built on an unclear or incorrect earlier task. It also keeps the developer in control of reviewing changes before continuing.

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.execute_interactively/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.execute_interactively/github.svg)](https://agentmods.dev/skills/causify-ai/helpers/auto_task.execute_interactively)

Your own site

<a href="https://agentmods.dev/skills/causify-ai/helpers/auto_task.execute_interactively"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/auto_task.execute_interactively/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.execute_interactively"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/auto_task.execute_interactively.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 1,136 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	$0.01136
Opus 5.5	$0.00006	$0.00454
Sonnet 5.5	$0.00003	$0.00227
Haiku 4.5	$0.00002	$0.00114

Measured 16d ago against content hash 5e350f350749, 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_interactively 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.

.claude/skills/auto_task.execute_interactively/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal

Execute an ordered list of well-specified, sequential tasks <FILE> specified by the user by alternating agent execution, human review, and commit in a branch
Create the GH issue, branch, and PR for <FILE> before starting the task loop: every auto_task maps to one GH issue implemented in one branch/PR (see .claude/skills/auto_task.rules.md)
Follow .claude/skills/auto_task.rules.md for how tasks are queued, specified, and named before they reach this skill

When to Use This Skill

Follow .claude/skills/auto_task.rules.md section "Ask for Clarification Before Executing an Unclear Plan" when a task's spec is unclear or incomplete

Conventions

Follow .claude/skills/auto_task.rules.md for queue, spec, naming, and coding/testing conventions

Constraints

Do create the GH issue, branch, and (draft) PR for <FILE> up front: this is part of this skill's job, not the user's
Do not commit any code change for a task: committing is user's decision
Do not merge any PR: merging is the user's decision

Workflow

Confirm the Task List

Read <FILE> and follow .claude/skills/auto_task.rules.md section "Confirm the Task List Before Executing" for the task list format and the problem/solution check
Make sure each task is clear and create a plan in 5 markdown bullets in <FILE> under each task
If the order or a dependency is unclear, follow .claude/skills/auto_task.rules.md section "Ask for Clarification Before Executing an Unclear Plan" before starting

Create the Issue and the Branch

Follow .claude/skills/auto_task.rules.md section "One GitHub Issue Is the Unit of Work": one GH issue covers the whole task list in <FILE>
Create the issue and the branch named after it (<RepoPrefix>Task<IssueNum>_<Description>) in one shot with git_create_issue_and_branch.py: it is more general than the raw invoke gh_issue_create / invoke git_branch_create tasks since it also branches submodules (e.g., helpers_root) symmetrically

Read the full file on GitHub · 111 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.

16d ago Changed · -1 lines 5e350f350749
29d ago Changed · +8 lines f6fde849e46d
1mo ago Changed · -10 lines c45dae75cafc
1mo ago Changed · +38 lines b4111451c580
1mo ago First seen · 76 lines · 15 tokens per session scan A fa63731ff6cc

Subscribe to this mod's changes

auto_task.execute_interactively 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 1,136 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.

Git and workflow Planning

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

Conventions

Constraints

Workflow

Confirm the Task List

Create the Issue and the Branch

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