run-task-loop

run-task-loop is a skill for Claude Code, Codex, Cursor from hlalljie/agent-workflow-presets. It costs 58 tokens per session (1,241 once invoked), scanned A, original, MIT.

A workflow for carrying a coding task from initial checks through implementation, tests, validation, and commit verification. It stops when work is blocked, needs an owner-only decision, or has no reasonable path forward.

In plain words
What is it for?
Use it to manage multi-step coding work, create or follow task lists, add tests, run tests, validate changes, and verify a commit.
Why use it?
It reduces the need for someone to repeatedly monitor and direct each step. It also keeps tasks and testing from being skipped.

Skill for Claude CodeCodexCursor

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.

agentmods
npx agentmods add skills/hlalljie/agent-workflow-presets/run-task-loop
Any agent
npx skills add hlalljie/agent-workflow-presets --skill run-task-loop
Clone the repo
git clone --depth 1 https://github.com/hlalljie/agent-workflow-presets

Made for: Claude Code, Codex, Cursor.

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.

agentmods badge for run-task-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/hlalljie/agent-workflow-presets/run-task-loop.svg)](https://agentmods.dev/skills/hlalljie/agent-workflow-presets/run-task-loop)
Your own site
<a href="https://agentmods.dev/skills/hlalljie/agent-workflow-presets/run-task-loop"><img src="https://agentmods.dev/badge/skills/hlalljie/agent-workflow-presets/run-task-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,241 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00058 $0.01241
Opus 5 $0.00029 $0.00620
Sonnet 5 $0.00012 $0.00248
Haiku 4.5 $0.00006 $0.00124

Measured 4d ago against content hash 245aab8fb66e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run-task-loop 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 4d 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.

.cursor/skills/run-task-loop/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run task loop

Goal

Finish the work with strong coverage, without owner involvement until done, blocked, or out of credible fixes.

Doc shape: This skill points at other skills (add-tests, run-tests, verify-commit) instead of inlining every instruction—modular by choice; if that becomes hard to follow, a future option is one consolidated runbook.

Stop only for

  • Blocker — decision, access, ambiguity, or rule that forbids proceeding (dependency-safety.mdc, data-safety.mdc, …).
  • Owner-only items in open-questions.md, plan, or tasks.
  • No viable path after reasonable retries.

Otherwise keep going.

First action: blockers

  1. Scan conversation, plan, open-questions.md, tasks for owner-only items.
  2. If blocking → list and stop; else proceed.

Task list (always a step)

The task file may already exist or not yet—either way, this step runs:

  • If there is no task file for the current scope: create one with create task list under .cursor/plans/**/tasks/*.md.
  • If it exists: open it and work from ### Task N in sequence.

Do not skip this step; scope and checkboxes live there.

Task cadence

Overrides default one-task-per-message in task-scope.mdc: in this invocation, implement Task 1, 2, 3… in order until the feature is done, you hit Stop only for, or Handoff—not only the first task.

Build loop

  1. Codebase survey (MANDATORY before any code) — Before writing any file or editing any component, read the existing codebase for the area you are touching:
    • Read docs/folder-structure.md for the canonical map of what lives where.
    • Read the reference implementation identified in .cursor/rules/repository-layout.mdc — the closest existing route, module, or component of the same type as what you're building.
    • Read any shared primitives (layout, shell, utilities) relevant to the task before creating new ones.
    • Match the patterns you find. Do not invent new folder names, new structural conventions, or new abstraction layers unless the task explicitly requires it and you explain why.
    • This step is not optional and cannot be skipped for speed. Producing code that doesn't match existing structure creates more rework than doing it right.

Read the full file on GitHub · 76 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.

  1. 4d ago First seen · 76 lines · 58 tokens per session scan A 245aab8fb66e

Subscribe to this mod's changes

run-task-loop is a skill published in the GitHub repository hlalljie/agent-workflow-presets (2 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 1,241 once invoked, about $0.0003 per session on Opus 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 2026-08-31.