New: 97,000+ 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

PRP Loop: Autonomous Pipeline

by Wirasm in Wirasm/prp

Runs a detached, resumable loop that plans, implements, opens a PR, reviews and fixes a feature across headless CLI sessions until the review is clean.

MITAuto-check passedAgent Workflows

Install PRP Loop: Autonomous Pipeline

skills CLI
$ npx skills add Wirasm/prp --skill prp-loop -a claude-code

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

GitHub CLI
$ gh skill install Wirasm/prp prp-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/Wirasm/prp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/prp-loop .claude/skills/prp-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
prp-loop
GitHub stars
2.3k
Token cost
~863 tokens
SKILL.md length
368 words
Files
2 (incl. scripts)
Skills in repo
37
Repo updated
First seen
Licence
MIT

At a glance

Runs a detached, resumable loop that plans, implements, opens a PR, reviews and fixes a feature across headless CLI sessions until the review is clean.

  • Works in 5 steps: plan — prp-plan writes the plan under… → implement — prp-implement executes and… → pr compatibility — if an older… → …
  • Running a full feature through plan, build, PR and review unattended
  • SKILL.md covers Run it, What it does, Safety and Notes
  • Runs Python scripts from its folder; calls uv and claude

What it does

This skill launches an orchestrator that drives a feature through plan, implement (commit and open a pull request), and review stages, each run as its own headless CLI session, and tracks progress in a JSON state file. A halted or interrupted run can be resumed from that state file rather than restarted.

By default it allows three review-and-fix cycles and ten implementation iterations, auto-detects the base branch, and can be told to stop after a particular stage, or given an authoritative pass or fail command to judge its own work. When a review comes back needing changes, the complete report, the plan and the live PR all feed into a fresh implementation pass that pushes a correction and triggers a re-review, looping until the PR is ready to merge or a limit is hit.

It runs fully autonomously with permission checks skipped, and refuses to operate directly on main, master, development or the repository's base branch - it only works from a feature branch.

When your agent uses it

  • Running a full feature through plan, build, PR and review unattended
  • Resuming a PRP loop that stopped partway through
  • Looping implementation and review until a PR passes cleanly

Example prompts

  • “Run the full PRP loop for the new billing export feature.”
  • “Resume the halted PRP loop from its saved state.”
  • “Run the PRP loop but stop once implementation is done, no review.”

Requirements

  • uv (to run the loop's Python script)
  • A feature branch separate from main

Workflow steps

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

  1. plan — prp-plan writes the plan under the project's PRP store at $PRP_DIR/plans/.plan.md.
  2. implement — prp-implement executes and validates the plan, commits the work, and opens the PR (bounded by --max-implement-iterations).
  3. pr compatibility — if an older implementation run did not open a PR, prp-pr does so once.
  4. review — prp-review runs its current default review, writes the canonical report, and publishes that complete report to GitHub.
  5. cycle — if the verdict needs fixes, the complete report, plan, and live PR feed into a fresh prp-implement correction pass → push →…

What it can do on your machine

Read from SKILL.md and the folder at commit 4352925. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • uv
    • claude

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

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    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

PRP Loop: Autonomous Pipeline loads about 863 tokens when it runs. Until then it costs about 107 tokens; SKILL.md has 368 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~107
When it runs · the whole SKILL.md, loaded when a task matches
~863

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); the scripts in this folder are not scanned.

SKILL.md

The full file from Wirasm/prp at commit 4352925, republished under its MIT licence (© Wirasm). 368 words, ~863 tokens.

Download SKILL.mdSave it as .claude/skills/prp-loop/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
prp-loop
description
Runs the detached, resumable PRP pipeline in fresh headless CLI sessions, cycling plan, implementation, PR, review, and corrections with persisted state and safety bounds. Use only when the user explicitly asks to "run the full PRP loop", "run this detached", "continue across context windows", use headless autonomous execution, resume a saved loop, or invokes /prp-loop. Use prp-issue for ordinary end-to-end delivery.
argument-hint
<feature description> [--base <branch>] [--max-cycles N] [--validate "<cmd>"] | --resume

PRP Loop — autonomous cyclic pipeline

Launch the orchestrator that drives plan → implement (commit + PR) → review and loops review → fix until the PR review is clean (or limits are hit). It runs headless claude -p once per stage and tracks progress in ~/.prp/<key>/state/prp-loop.state.json.

Run it

Start a new loop with the user's request as the feature argument:

bash
uv run .claude/skills/prp-loop/scripts/prp_loop.py "$ARGUMENTS"

Resume a halted or in-progress loop:

bash
uv run .claude/skills/prp-loop/scripts/prp_loop.py --resume

Defaults: --max-cycles 3, --max-implement-iterations 10, base branch auto-detected. Pass --validate "<cmd>" to give the loop an authoritative green check (exit 0 = pass).

Stop after a stage (--until)

Pass --until <stage> (plan | implement | pr | review | fix) to halt once that stage completes:

bash
uv run .claude/skills/prp-loop/scripts/prp_loop.py "$ARGUMENTS" --until implement

--until implement runs plan → implement and stops once validations are green and the implementation skill has committed and opened its PR — no review.

UX note: the retired Ralph loop was single-session and interactive (a Stop-hook fed the prompt back in the same session). prp-loop --until implement is headless instead — it drives fresh claude -p sessions per iteration and you resume/inspect via the state file rather than watching it live.

Show full SKILL.md (196 more words)Show less

What it does

  1. plan — prp-plan writes the plan under the project's PRP store at $PRP_DIR/plans/<feature>.plan.md.
  2. implement — prp-implement executes and validates the plan, commits the work, and opens the PR (bounded by --max-implement-iterations).
  3. pr compatibility — if an older implementation run did not open a PR, prp-pr does so once.
  4. review — prp-review runs its current default review, writes the canonical report, and publishes that complete report to GitHub.
  5. cycle — if the verdict needs fixes, the complete report, plan, and live PR feed into a fresh prp-implement correction pass → push → re-review, up to --max-cycles. Ready to merge → done; review incomplete → halt.

Safety

  • Fully autonomous (--dangerously-skip-permissions). Operates only on the feature branch — it refuses to PR from main/master/development/the base branch.
  • Halts with state preserved on: implement/fix not green after the iteration limit, review still dirty after --max-cycles, a fix pass with no new commit (no progress), failed push, or any stage error.
  • Inspect or resume via ~/.prp/<key>/state/prp-loop.state.json.

Notes

This orchestrator is self-contained and uses no Stop-hook. It owns both loops itself and detects "green" from each stage's VALIDATION: GREEN sentinel (or the --validate command). The PRP skills it calls are invoked verbatim and never modified.

© Wirasm, 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 1 other file (scripts) in .claude/skills/prp-loop of Wirasm/prp.

  • SKILL.md
  • scripts/prp_loop.py

Open the folder on GitHubat commit 4352925

Compare with similar skills

PRP Loop: Autonomous Pipeline 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.

PRP Loop: Autonomous Pipeline compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
PRP Loop: Autonomous Pipeline this skillWirasm/prp2.3k—~863Automated safety check: PassMIT
Implement FeatureDevBetterCom/DevBetterWeb157—~1.5kAutomated safety check: PassNone
Spektacular Plan Implementationjumppad-labs/jumppad263—~1.8kAutomated safety check: PassMPL-2.0
Next Task Implementation Loopbreaking-brake/cc-wf-studio5.4k—~2.1kAutomated safety check: PassCustom licence
LFG Autonomous DeliveryEveryInc/compound-engineering-plugin25k—~2kAutomated safety check: PassMIT
Pull Platformplatform Changesplatformplatform/PlatformPlatform440—~2.7kAutomated safety check: NotesMIT

Similar skills

  • Implement Feature

    DevBetterCom/DevBetterWeb

    End-to-end workflow for implementing, fixing, or otherwise working on a specific GitHub issue.

    157 GitHub stars~1.5k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed

  • Spektacular Plan Implementation

    jumppad-labs/jumppad

    Executes an approved plan step by step through the spektacular CLI, which acts as the state machine, producing code, tests and a changelog.

    263 GitHub stars~1.8k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check passed

  • Next Task Implementation Loop

    breaking-brake/cc-wf-studio

    Runs one unattended implementation iteration of an autonomous loop: steward the in-flight PR, fix interrupts, or build one queued idea issue and open a PR.

    5.4k GitHub stars~2.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • LFG Autonomous Delivery

    EveryInc/compound-engineering-plugin

    Takes a request all the way through without stopping, routing it to Compound Engineering skills so that a code change ends as an open pull request.

    25k GitHub stars~2k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Pull Platformplatform Changes

    platformplatform/PlatformPlatform

    Pull unmerged PlatformPlatform pull requests into a downstream project by cherry-picking each one onto the platformplatform-updates branch.

    440 GitHub stars~2.7k tokensUpdated 13 days ago
    Agent WorkflowsAuto-check: notes

  • 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

More from Wirasm/prp

All 37 skills in this repo

  • PRP Loop

    Wirasm/prp

    Runs the plan, implement and review pipeline detached in fresh headless sessions, looping review and fix until the pull request is clean.

    2.3k GitHub stars~894 tokensUpdated 5 days ago
    Auto-check passed

  • PRP Workstream Orchestrator

    Wirasm/prp

    Coordinates several PRP workstreams in isolated Git worktrees from one session, verifying proof, holding merge gates and sequencing the merges.

    2.3k GitHub stars~3.5k tokensUpdated 5 days ago
    Auto-check passed

  • PRP Implementation Planner

    Wirasm/prp

    Turns a PRD, issue or description into an implementation-ready plan grounded in codebase evidence, adding root-cause analysis for bugs and publishing issue plans back to the issue.

    2.3k GitHub stars~4.1k tokensUpdated 5 days ago
    Auto-check passed

  • PRP Plan

    Wirasm/prp

    Writes an implementation-ready plan for a feature, bug fix, refactor or chore from a PRD, issue or description, grounded in codebase evidence, and can post it back to the source issue.

    2.3k GitHub stars~4k tokensUpdated 5 days ago
    Auto-check passed

  • PRP Spike

    Wirasm/prp

    Settles a feasibility question with the smallest throwaway build that could disprove it, in an isolated worktree, ending in a verdict backed by evidence instead of a PR.

    2.3k GitHub stars~3.8k tokensUpdated 5 days ago
    Auto-check passed

  • PRP Spike

    Wirasm/prp

    Settles a feasibility or fit question by building the smallest throwaway artifact that could prove it wrong, in an isolated worktree, ending in a PROVEN, DISPROVEN or CONDITIONAL verdict.

    2.3k GitHub stars~3.8k tokensUpdated 5 days ago
    Auto-check passed

Categories

Questions about PRP Loop: Autonomous Pipeline

What does PRP Loop: Autonomous Pipeline do?

Runs a detached, resumable loop that plans, implements, opens a PR, reviews and fixes a feature across headless CLI sessions until the review is clean. This skill launches an orchestrator that drives a feature through plan, implement (commit and open a pull request), and review stages, each run as its own headless CLI session, and tracks progress in a JSON state file. A halted or interrupted run can be resumed from that state file rather than restarted.

When should I use PRP Loop: Autonomous Pipeline?

PRP Loop: Autonomous Pipeline fits situations like: running a full feature through plan, build, PR and review unattended; resuming a PRP loop that stopped partway through; looping implementation and review until a PR passes cleanly.

How do I install PRP Loop: Autonomous Pipeline in Claude Code?

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

How do I install PRP Loop: Autonomous Pipeline in Codex?

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

Can I use PRP Loop: Autonomous Pipeline 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 Wirasm/prp --skill prp-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/prp-loop, .gemini/skills/prp-loop, .github/skills/prp-loop and .opencode/skills/prp-loop in your project.

What does PRP Loop: Autonomous Pipeline need to run?

Going by SKILL.md and its folder, PRP Loop: Autonomous Pipeline needs Python for the scripts in its folder and the command-line tools its instructions call (uv and claude). Our summary lists: uv (to run the loop's Python script); A feature branch separate from main.

Does PRP Loop: Autonomous Pipeline access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is PRP Loop: Autonomous Pipeline 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does PRP Loop: Autonomous Pipeline use?

PRP Loop: Autonomous Pipeline 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 PRP Loop: Autonomous Pipeline use?

About 863 tokens (SKILL.md is roughly 3.5k 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 PRP Loop: Autonomous Pipeline?

Skills that share tags, products or a category with PRP Loop: Autonomous Pipeline: Implement Feature (DevBetterCom/DevBetterWeb, 157 stars), Spektacular Plan Implementation (jumppad-labs/jumppad, 263 stars), Next Task Implementation Loop (breaking-brake/cc-wf-studio, 5.4k stars) and LFG Autonomous Delivery (EveryInc/compound-engineering-plugin, 25k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PRP Loop: Autonomous Pipeline?

Wirasm (a GitHub user) maintains it in Wirasm/prp, which has 2,258 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 2, 2026.

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