New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Long Running Agent

by mikeOnBreeze in mikeOnBreeze/cc-crossbeam

This skill converts planning docs and specs into phase-based task structures and prompts for long-running Claude agents.

MITAuto-check passedAgent Workflows

Install Long Running Agent

skills CLI
$ npx skills add mikeOnBreeze/cc-crossbeam --skill long-running-agent -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mikeOnBreeze/cc-crossbeam long-running-agent --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mikeOnBreeze/cc-crossbeam.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/long-running-agent .claude/skills/long-running-agent && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
long-running-agent
GitHub stars
293
Token cost
~1k tokens
SKILL.md length
392 words
Files
3 (incl. assets)
Skills in repo
20
Repo updated
First seen
Licence
MIT

At a glance

This skill converts planning docs and specs into phase-based task structures and prompts for long-running Claude agents.

  • Works in 6 steps: Gather Inputs → Read the Blog → Decompose into Phases and Tasks → …
  • Setting up a multi-session agent workflow
  • SKILL.md covers When to Use This Skill, Source of Truth, Core Workflow and Output Structure, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Long Running Agent is an agent skill from mikeOnBreeze/cc-crossbeam. This skill converts planning docs and specs into phase-based task structures and prompts for long-running Claude agents. Use when setting up a multi-session agent workflow or breaking down a spec into phases with verification checkpoints.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including assets (for example `assets/claude-prompt-template.md` and `assets/task-template.json`).

It sits in Agent Workflows, covering Autonomous loops. The repository describes itself as: CrossBeam Permits — AI-assisted building-permit plan review for cities and builders. The licence is MIT.

When your agent uses it

  • Setting up a multi-session agent workflow
  • Breaking down a spec into phases with verification checkpoints

Example prompts

  • “/long-running-agent”

Requirements

  • Node.js

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Gather Inputs
  2. Read the Blog
  3. Decompose into Phases and Tasks
  4. Generate claude-task.json
  5. Generate claude-prompt.md
  6. Keep the SPEC

What it can do on your machine

Read from SKILL.md and the folder at commit cc5591e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • anthropic.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Long Running Agent loads about 1k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 392 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mikeOnBreeze/cc-crossbeam at commit cc5591e, republished under its MIT licence (© mikeOnBreeze). 392 words, ~1,001 tokens.

Download SKILL.mdSave it as .claude/skills/long-running-agent/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
long-running-agent
description
This skill converts planning docs and specs into phase-based task structures and prompts for long-running Claude agents. Use when setting up a multi-session agent workflow or breaking down a spec into phases with verification checkpoints.

Long-Running Agent Setup

Convert specs and planning documents into phase-based task structures for autonomous multi-session execution.

When to Use This Skill

  • User has a spec or planning doc to execute with a long-running agent
  • User wants to break down a project into phases with verification checkpoints
  • User wants to create a claude-prompt.md for autonomous task execution

Source of Truth

Before doing anything, fetch and read this blog post for the core patterns: https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents

This blog from Anthropic's engineering team defines the effective patterns. Apply them directly.

Core Workflow

1. Gather Inputs

Request from the user:

  • Spec/Planning Doc: The document to convert (required)
  • Project Name: Short identifier
  • Output Location: Where to create files
2. Read the Blog

Fetch the Anthropic blog post above. The key patterns are:

  • Phase-based work with verification checkpoints
  • Explicit feature/task enumeration (granular, testable items)
  • Task file as progress tracker
  • Git checkpointing after each task
  • Strong constraints (no test deletion, no skipping phases)
3. Decompose into Phases and Tasks

Break the spec into:

Phases (3-8 typically):

  • Logical groupings of related work
  • Each phase has verification steps to test completion
  • Agent completes ALL tasks in a phase, then stops for user verification

Tasks (per phase):

  • Granular, implementable units
  • Each task has specific steps
  • Uses passes: true/false to track completion

Example structure from a real project:

Phase 1: Project Foundation (3 tasks)
  - setup-001: Initialize project structure
  - setup-002: Create environment config
  - types-001: Define core interfaces
  Verification: "Run npx tsc --noEmit, confirm no errors"

Phase 2: Storage & Skills (5 tasks)
  - storage-001: Create storage interface
  - skill-001 to skill-004: Create skill files
  Verification: "Confirm skills load, storage works"

... etc
4. Generate claude-task.json

Create the task file using assets/task-template.json structure:

  • phases array with verification steps
  • tasks array with passes: false initially
  • Tasks reference their parent phase

Output: {project-root}/claude-task.json

Show full SKILL.md (148 more words)Show less
5. Generate claude-prompt.md

Use assets/claude-prompt-template.md as the base.

Key sections to customize:

  • Project overview and goal
  • Key files list (SPEC.md, claude-task.json, any API docs)
  • Phases table showing all phases
  • File structure target
  • Technical decisions specific to the project

Output: {project-root}/claude-prompt.md

6. Keep the SPEC

The original spec should remain as SPEC.md for the agent to reference when it needs detailed requirements.

Output Structure

{project-root}/
├── claude-prompt.md      # Agent instructions
├── claude-task.json      # Phases and tasks
└── SPEC.md               # Original planning doc (kept for reference)

Starting the Agent

Instruct the user:

@claude-prompt.md

The agent will read claude-task.json, find the current phase, and work through tasks until phase completion.

Key Patterns (from the blog)

  1. Phase boundaries = verification checkpoints - Agent stops, user verifies, then continues
  2. Complete ALL tasks in phase - No stopping mid-phase
  3. Git commit after each task - task-XXX: description
  4. Never skip phases - Sequential progression
  5. Task file is the source of truth - Agent reads and updates it

Reference Materials

  • assets/claude-prompt-template.md - Template for claude-prompt.md
  • assets/task-template.json - Template for claude-task.json structure

© mikeOnBreeze, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (assets) in .claude/skills/long-running-agent of mikeOnBreeze/cc-crossbeam.

  • SKILL.md
  • assets/claude-prompt-template.md
  • assets/task-template.json

Open the folder on GitHubat commit cc5591e

Compare with similar skills

Long Running Agent next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Long Running Agent compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Long Running Agent this skillmikeOnBreeze/cc-crossbeam293—~1kAutomated safety check: PassMIT
Show Me Your Work Decision Logcursor/plugins11k8 repos~1.6kAutomated safety check: PassNone
Autoresearch Iteration Loopuditgoenka/autoresearch6.5k1 repos~2kAutomated safety check: PassMIT
Install Loop Engineeringcobusgreyling/loop-engineering11k1 repos~648Automated safety check: PassMIT
LoopyForward-Future/loopy3.2k—~3.9kAutomated safety check: PassMIT
AI Performance Improvement Plantanweai/pua20k2 repos~6.9kAutomated safety check: PassMIT

Similar skills

  • Show Me Your Work Decision Log

    cursor/plugins

    Official

    Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.

    11k GitHub starsUsed in 8 repos~1.6k tokens
    Agent WorkflowsAuto-check passed

  • Autoresearch Iteration Loop

    uditgoenka/autoresearch

    Runs an autonomous modify, verify, keep-or-discard loop against any metric, with subcommands for planning, debugging, fixing, security audits, shipping and more.

    6.5k GitHub starsUsed in 1 repo~2k tokens
    Agent WorkflowsAuto-check passed

  • Install Loop Engineering

    cobusgreyling/loop-engineering

    Installs Loop Engineering into a project through the single @cobusgreyling/loop CLI, scaffolding a report-only loop and a readiness score.

    11k GitHub starsUsed in 1 repo~648 tokens
    Agent WorkflowsAuto-check passed

  • Loopy

    Forward-Future/loopy

    Discover, find, compare, audit, repair, adapt, craft, run, debrief, save, and prepare repeatable AI-agent loops for publication.

    3.2k GitHub stars~3.9k tokensUpdated 29 days ago
    Agent WorkflowsAuto-check passed

  • AI Performance Improvement Plan

    tanweai/pua

    Pushes an agent to exhaust every option, investigate before asking and take initiative beyond the literal request, instead of giving up or waiting passively.

    20k GitHub starsUsed in 2 repos~6.9k tokens
    Agent WorkflowsAuto-check passed

  • LoopX Self Repair

    loopx-project/loopx

    Diagnoses surprising LoopX behavior, such as stale recommendations or tiny progress, assigns it to the responsible layer and repairs it at the lowest durable level.

    6.2k GitHub stars~2.2k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from mikeOnBreeze/cc-crossbeam

All 20 skills in this repo

  • Adu PDF Extraction

    mikeOnBreeze/cc-crossbeam

    This skill extracts construction PDF plan binders into agent-consumable formats.

    293 GitHub stars~5k tokensUpdated 7 mo ago
    Auto-check passed

  • Adu Targeted Page Viewer

    mikeOnBreeze/cc-crossbeam

    Extracts construction plan PDFs into page PNGs, reads the sheet index to build a sheet-to-page manifest, and enables targeted viewing of specific sheets.

    293 GitHub stars~1.8k tokensUpdated 7 mo ago
    Auto-check passed

  • Fal AI

    mikeOnBreeze/cc-crossbeam

    This skill enables AI video generation from images AND text-to-speech voiceover generation using Fal.ai's API.

    293 GitHub stars~1.9k tokensUpdated 7 mo ago
    Auto-check: notes

  • Nano Banana

    mikeOnBreeze/cc-crossbeam

    This skill enables image generation and editing using Google's Gemini Nano Banana models.

    293 GitHub stars~944 tokensUpdated 7 mo ago
    Auto-check: notes

  • Adu City Research

    mikeOnBreeze/cc-crossbeam

    Researches city-level ADU regulations, municipal codes, and standard details for any California city.

    293 GitHub stars~3.9k tokensUpdated 7 mo ago
    Auto-check passed

  • Adu Plan Review

    mikeOnBreeze/cc-crossbeam

    City-side ADU plan review — the flip side of adu-corrections-flow.

    293 GitHub stars~3.7k tokensUpdated 7 mo ago
    Auto-check passed

Categories

Questions about Long Running Agent

What does Long Running Agent do?

This skill converts planning docs and specs into phase-based task structures and prompts for long-running Claude agents. Long Running Agent is an agent skill from mikeOnBreeze/cc-crossbeam. This skill converts planning docs and specs into phase-based task structures and prompts for long-running Claude agents.

When should I use Long Running Agent?

Long Running Agent fits situations like: setting up a multi-session agent workflow; breaking down a spec into phases with verification checkpoints.

How do I install Long Running Agent in Claude Code?

Run `npx skills add mikeOnBreeze/cc-crossbeam --skill long-running-agent -a claude-code`. Or copy the skill folder (.claude/skills/long-running-agent in mikeOnBreeze/cc-crossbeam) into .claude/skills/long-running-agent in your project. Claude Code loads it when a task matches its description.

How do I install Long Running Agent in Codex?

Run `npx skills add mikeOnBreeze/cc-crossbeam --skill long-running-agent -a codex`. Or copy the skill folder (.claude/skills/long-running-agent in mikeOnBreeze/cc-crossbeam) into .agents/skills/long-running-agent in your project. Codex loads it when a task matches its description.

Can I use Long Running Agent in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mikeOnBreeze/cc-crossbeam --skill long-running-agent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/long-running-agent, .gemini/skills/long-running-agent, .github/skills/long-running-agent and .opencode/skills/long-running-agent in your project.

What does Long Running Agent need to run?

SKILL.md names no scripts, command-line tools or credentials: Long Running Agent is instructions for the agent only. Our summary lists: Node.js.

Does Long Running Agent access the network?

SKILL.md names 1 domain. As links in the text: anthropic.com. This is read from the text; nothing was executed.

Is Long Running Agent safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Long Running Agent use?

Long Running Agent is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Long Running Agent use?

About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Long Running Agent?

Skills that share tags, products or a category with Long Running Agent: Show Me Your Work Decision Log (cursor/plugins, 11k stars), Autoresearch Iteration Loop (uditgoenka/autoresearch, 6.5k stars), Install Loop Engineering (cobusgreyling/loop-engineering, 11k stars) and Loopy (Forward-Future/loopy, 3.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Long Running Agent?

mikeOnBreeze (a GitHub user) maintains it in mikeOnBreeze/cc-crossbeam, which has 293 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on March 2, 2026.

Source: mikeOnBreeze/cc-crossbeam on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.