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

by Wirasm in Wirasm/prp

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

MITAuto-check passedAgent Workflows

Install PRP Loop

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/.agents/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
~894 tokens
SKILL.md length
396 words
Files
2 (incl. scripts)
Skills in repo
37
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 5 steps: plan — prp-plan writes the plan under… → implement — prp-implement executes and… → pr compatibility — if an older… → …
  • Asked to run the full PRP loop for a feature
  • SKILL.md covers Run it, What it does, Safety and Notes
  • Runs Python scripts from its folder; calls uv and codex

What it does

This starts an orchestrator that takes a feature through plan, implement (commit and open a PR) and review, then loops review and fix until the PR review comes back clean or a limit is hit. Each stage runs as a fresh headless codex exec session, and progress is saved in a state file under ~/.prp, so a halted loop can be picked up again with --resume. Defaults are three review-fix cycles and ten implementation iterations with the base branch detected automatically, and a --validate command gives the loop an authoritative pass check.

The stages hand off to sibling skills: prp-plan writes the plan file, prp-implement executes and validates it, commits and opens the PR, prp-pr opens one if an older run did not, and prp-review writes a report and publishes it to GitHub. When fixes are needed, the report, plan and live PR feed a fresh correction pass, a push and a re-review. The --until option halts after a chosen stage. It is for explicit requests such as running detached or across context windows, while prp-issue handles ordinary delivery. The excerpt ends before the safety section.

When your agent uses it

  • Asked to run the full PRP loop for a feature
  • Running plan, implementation and review detached from the current session
  • Continuing a long job across context windows
  • Resuming a halted loop from its saved state

Example prompts

  • “Run the full PRP loop for adding CSV export, detached.”
  • “Resume the halted prp loop.”
  • “Run the loop for the new search filter, but stop once the PR is open and validations pass.”

Requirements

  • The codex CLI
  • uv to run the loop script
  • GitHub access for the pull request and review report
  • The prp-plan, prp-implement, prp-pr and prp-review skills

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
    • codex

    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 loads about 894 tokens when it runs. Until then it costs about 107 tokens; SKILL.md has 396 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
~894

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). 396 words, ~894 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.

Arguments: $ARGUMENTS (and $1, $2, ...) refer to the arguments given when this skill was invoked. Take them from the user's request; if absent, infer them from the conversation.

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 codex exec 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 .agents/skills/prp-loop/scripts/prp_loop.py "$ARGUMENTS" --cli codex

Resume a halted or in-progress loop:

bash
uv run .agents/skills/prp-loop/scripts/prp_loop.py --resume --cli codex

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 .agents/skills/prp-loop/scripts/prp_loop.py "$ARGUMENTS" --cli codex --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 codex exec 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 .agents/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 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 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
PRP Loop this skillWirasm/prp2.3k—~894Automated safety check: PassMIT
Next Task Implementation Loopbreaking-brake/cc-wf-studio5.4k—~2.1kAutomated safety check: PassCustom licence
GitHub Review Iterationprisma/orm48k—~2.2kAutomated safety check: PassApache-2.0
Cherry Studio PR ReviewCherryHQ/cherry-studio52k—~3.9kAutomated safety check: PassAGPL-3.0
PR Reviewjaemk/self_update961—~1.5kAutomated safety check: NotesMIT
Plannotator Referencebacknotprop/plannotator9.2k—~5.7kAutomated safety check: WarnApache-2.0

Similar skills

  • 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 yesterday
    Agent WorkflowsAuto-check passed

  • GitHub Review Iteration

    prisma/orm

    Official

    Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

    48k GitHub stars~2.2k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Cherry Studio PR Review

    CherryHQ/cherry-studio

    Reviews Cherry Studio branches, pull requests, commits, files and docs against the project's own architecture, naming, API-boundary and UI rules, report-only by default.

    52k GitHub stars~3.9k tokensUpdated today
    DevelopmentAuto-check passed

  • PR Review

    jaemk/self_update

    Targeted, read-only review of a PR or checked-out branch. An agent skill from jaemk/self_update.

    961 GitHub stars~1.5k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes

  • Plannotator Reference

    backnotprop/plannotator

    Reference for picking the right Plannotator tool or command for plan review, code review, annotating files and URLs, archived plan decisions and Guided Reviews.

    9.2k GitHub stars~5.7k tokensUpdated yesterday
    DevelopmentAuto-check: warnings

  • Swarm PR Feedback Closer

    ZaxbyHub/opencode-swarm

    Ingests existing pull request feedback such as review comments and CI failures, verifies each claim, fixes confirmed issues and reports closure status for every item.

    488 GitHub stars~14k tokensUpdated today
    DevelopmentAuto-check passed

More from Wirasm/prp

All 37 skills in this repo

  • PRP Loop: Autonomous Pipeline

    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.

    2.3k GitHub stars~863 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

Works with

Categories

Questions about PRP Loop

What does PRP Loop do?

Runs the plan, implement and review pipeline detached in fresh headless sessions, looping review and fix until the pull request is clean. This starts an orchestrator that takes a feature through plan, implement (commit and open a PR) and review, then loops review and fix until the PR review comes back clean or a limit is hit.prp, so a halted loop can be picked up again with --resume.

When should I use PRP Loop?

PRP Loop fits situations like: asked to run the full PRP loop for a feature; running plan, implementation and review detached from the current session; continuing a long job across context windows; resuming a halted loop from its saved state.

How do I install PRP Loop in Claude Code?

Run `npx skills add Wirasm/prp --skill prp-loop -a claude-code`. Or copy the skill folder (.agents/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 in Codex?

Run `npx skills add Wirasm/prp --skill prp-loop -a codex`. Or copy the skill folder (.agents/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 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 need to run?

Going by SKILL.md and its folder, PRP Loop needs Python for the scripts in its folder and the command-line tools its instructions call (uv and codex). Our summary lists: The codex CLI; uv to run the loop script; GitHub access for the pull request and review report; The prp-plan, prp-implement, prp-pr and prp-review skills.

Does PRP Loop 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 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 use?

PRP 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 PRP Loop use?

About 894 tokens (SKILL.md is roughly 3.6k 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?

Skills that share tags, products or a category with PRP Loop: Next Task Implementation Loop (breaking-brake/cc-wf-studio, 5.4k stars), GitHub Review Iteration (prisma/orm, 48k stars), Cherry Studio PR Review (CherryHQ/cherry-studio, 52k stars) and PR Review (jaemk/self_update, 961 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PRP Loop?

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.