Agent skill

Ralph Loop

by charfeng1 in charfeng1/opencode-ralph-loop

Start Ralph Loop - auto-continues until task completion. An agent skill from charfeng1/opencode-ralph-loop.

MITAuto-check passedAgent Workflows

Install Ralph Loop

skills CLI
$ npx skills add charfeng1/opencode-ralph-loop --skill ralph-loop -a claude-code

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

GitHub CLI
$ gh skill install charfeng1/opencode-ralph-loop ralph-loop --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/charfeng1/opencode-ralph-loop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ralph-loop .claude/skills/ralph-loop && 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
ralph-loop
GitHub stars
112
Token cost
~517 tokens
SKILL.md length
235 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Start Ralph Loop - auto-continues until task completion. An agent skill from charfeng1/opencode-ralph-loop.

  • Works in 4 steps: You work on the task until you go idle → The plugin detects the idle state and… → If not complete, it prompts you to… → …
  • Tasks that involve Autonomous loops
  • SKILL.md covers How It Works, Starting the Loop, Completion Promise - CRITICAL… and Checking Status, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ralph Loop is an agent skill from charfeng1/opencode-ralph-loop. Start Ralph Loop - auto-continues until task completion

Its SKILL.md is about 520 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Autonomous loops. The repository describes itself as: Minimal Ralph Loop plugin for opencode - auto-continues until task completion. The licence is MIT.

When your agent uses it

  • Tasks that involve Autonomous loops

Example prompts

  • “/ralph-loop”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. You work on the task until you go idle
  2. The plugin detects the idle state and checks for completion
  3. If not complete, it prompts you to continue where you left off
  4. This repeats until you output the completion promise or max iterations reached

What it can do on your machine

Read from SKILL.md and the folder at commit 2ef2386. 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 (its code samples are bash and markdown).

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

  • Network

    No URLs in SKILL.md.

    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

Ralph Loop loads about 517 tokens when it runs. Until then it costs about 17 tokens; SKILL.md has 235 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~17
When it runs · the whole SKILL.md, loaded when a task matches
~517

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 charfeng1/opencode-ralph-loop at commit 2ef2386, republished under its MIT licence (© charfeng1). 235 words, ~517 tokens.

Download SKILL.mdSave it as .claude/skills/ralph-loop/SKILL.md (or your agent's skills folder).
name
ralph-loop
description
Start Ralph Loop - auto-continues until task completion

Ralph Loop

Start an iterative development loop that automatically continues until the task is complete.

How It Works

The Ralph Loop creates a continuous feedback cycle for completing complex tasks:

  1. You work on the task until you go idle
  2. The plugin detects the idle state and checks for completion
  3. If not complete, it prompts you to continue where you left off
  4. This repeats until you output the completion promise or max iterations reached

Your previous work remains accessible through files and git history, enabling progressive refinement across iterations.

Starting the Loop

When you invoke this skill, create the state file in the project directory:

bash
mkdir -p .opencode && cat > .opencode/ralph-loop.local.md << 'EOF'
---
active: true
iteration: 0
maxIterations: 100
---

[The user's task prompt goes here]
EOF

Then inform the user and begin working on the task.

Completion Promise - CRITICAL RULES

When you have FULLY completed the task, signal completion by outputting:

<promise>DONE</promise>

IMPORTANT CONSTRAINTS:

  • ONLY output <promise>DONE</promise> when the task is COMPLETELY and VERIFIABLY finished
  • The statement MUST be completely and unequivocally TRUE
  • Do NOT output false promises to escape the loop, even if you think you're stuck
  • Do NOT lie even if you think you should exit for other reasons
  • If you're blocked, explain the blocker and request help instead of falsely completing

The loop can only be stopped by:

  1. Truthful completion promise
  2. Max iterations reached
  3. User running /cancel-ralph

Checking Status

Check current iteration:

bash
grep '^iteration:' .opencode/ralph-loop.local.md

State File Format

The state file at .opencode/ralph-loop.local.md uses YAML frontmatter:

markdown
---
active: true
iteration: 3
maxIterations: 100
sessionId: ses_abc123
---

Your original task prompt

Add .opencode/ralph-loop.local.md to your .gitignore.

© charfeng1, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/ralph-loop of charfeng1/opencode-ralph-loop.

Open the folder on GitHubat commit 2ef2386

Compare with similar skills

Ralph Loop 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.

Ralph Loop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ralph Loop this skillcharfeng1/opencode-ralph-loop112—~517Automated safety check: PassMIT
Show Me Your Work Decision Logcursor/plugins10k9 repos~1.6kAutomated safety check: PassNone
Autoresearch Iteration Loopuditgoenka/autoresearch6.5k1 repos~2kAutomated safety check: PassMIT
PUA Looptanweai/pua20k1 repos~1.1kAutomated safety check: PassMIT
AutopilotYeachan-Heo/oh-my-claudecode40k1 repos~4.4kAutomated safety check: PassMIT
Install Loop Engineeringcobusgreyling/loop-engineering11k1 repos~648Automated safety check: PassMIT

Similar skills

  • 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.

    10k GitHub starsUsed in 9 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
  • PUA Loop

    tanweai/pua

    Runs an unattended iterate-until-verified loop in which a user-set verify command, not the agent's own claim, decides when the task is finished.

    20k GitHub starsUsed in 1 repo~1.1k tokens
    Agent WorkflowsAuto-check passed
  • Autopilot

    Yeachan-Heo/oh-my-claudecode

    Takes a short product idea through requirements, design, planning, parallel implementation, QA cycles and multi-reviewer validation to produce working code.

    40k GitHub starsUsed in 1 repo~4.4k 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 27 days ago
    Agent WorkflowsAuto-check passed

More from charfeng1/opencode-ralph-loop

  • Help

    charfeng1/opencode-ralph-loop

    Explain Ralph Loop plugin and available commands. An agent skill from charfeng1/opencode-ralph-loop.

    112 GitHub stars~405 tokensUpdated 1 mo ago
    Auto-check passed
  • Cancel Ralph

    charfeng1/opencode-ralph-loop

    Cancel active Ralph Loop

    112 GitHub stars~222 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Ralph Loop

What does Ralph Loop do?

Start Ralph Loop - auto-continues until task completion. An agent skill from charfeng1/opencode-ralph-loop. Ralph Loop is an agent skill from charfeng1/opencode-ralph-loop.

When should I use Ralph Loop?

Ralph Loop fits situations like: tasks that involve Autonomous loops.

How do I install Ralph Loop in Claude Code?

Run `npx skills add charfeng1/opencode-ralph-loop --skill ralph-loop -a claude-code`. Or copy the skill folder (skills/ralph-loop in charfeng1/opencode-ralph-loop) into .claude/skills/ralph-loop in your project. Claude Code loads it when a task matches its description.

How do I install Ralph Loop in Codex?

Run `npx skills add charfeng1/opencode-ralph-loop --skill ralph-loop -a codex`. Or copy the skill folder (skills/ralph-loop in charfeng1/opencode-ralph-loop) into .agents/skills/ralph-loop in your project. Codex loads it when a task matches its description.

Can I use Ralph Loop 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 charfeng1/opencode-ralph-loop --skill ralph-loop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ralph-loop, .gemini/skills/ralph-loop, .github/skills/ralph-loop and .opencode/skills/ralph-loop in your project.

What does Ralph Loop need to run?

SKILL.md names no scripts, command-line tools or credentials: Ralph Loop is instructions for the agent only.

Does Ralph Loop access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ralph Loop 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 Ralph Loop use?

Ralph Loop 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 Ralph Loop use?

About 517 tokens (SKILL.md is roughly 2.1k 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 Ralph Loop?

Skills that share tags, products or a category with Ralph Loop: Show Me Your Work Decision Log (cursor/plugins, 10k stars), Autoresearch Iteration Loop (uditgoenka/autoresearch, 6.5k stars), PUA Loop (tanweai/pua, 20k stars) and Autopilot (Yeachan-Heo/oh-my-claudecode, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ralph Loop?

charfeng1 (a GitHub user) maintains it in charfeng1/opencode-ralph-loop, which has 112 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 8, 2026.

Source: charfeng1/opencode-ralph-loop on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.