An automated development workflow that moves a coding task through planning, implementation, pull-request creation, review, and corrections. It runs stages in separate command-line sessions and saves its progress so work can continue later.

It helps run a complete plan-to-review cycle, repeat fixes after review, and stop after a chosen stage. You can also set cycle, iteration, and validation limits.

It reduces the need to manually restart and coordinate each stage of a long coding task. Persisted state also helps resume work across sessions or context windows.

prp-loop — Skill by Wirasm

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/wirasm/prp/prp-loop

Any agent

npx skills add Wirasm/prp --skill prp-loop

Clone the repo

git clone --depth 1 https://github.com/Wirasm/prp

Made for: Claude Code, Codex.

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 889 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.

Model	Per session	Once invoked
Fable 5	$0.00095	$0.00889
Opus 5	$0.00048	$0.00445
Sonnet 5	$0.00019	$0.00178
Haiku 4.5	$0.00010	$0.00089

Measured 2d ago against content hash 818a91408bf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prp-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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/prp_loop.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/prp-loop/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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:

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

Resume a halted or in-progress loop:

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:

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.

What it does

plan — prp-plan writes the plan under the project's PRP store at $PRP_DIR/plans/<feature>.plan.md.
implement — prp-implement executes and validates the plan, commits the work, and opens the PR (bounded by --max-implement-iterations).
pr compatibility — if an older implementation run did not open a PR, prp-pr does so once.
review — prp-review runs its current default review, writes the canonical report, and publishes that complete report to GitHub.
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.

Read the full file on GitHub · 57 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/prp_loop.py 24 KB runs code

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.

2d ago First seen · 57 lines · 95 tokens per session scan A 818a91408bf6

Subscribe to this mod's changes

prp-loop is a skill published in the GitHub repository Wirasm/prp (2,240 stars, last pushed 4d ago), licensed MIT. It adds 95 tokens to every session and 889 once invoked, about $0.0005 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 2026-08-30.

Code review Memory and context Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens