A task runner for a PRP, a written implementation plan whose tasks are executed by separate Claude sessions. It starts, monitors, and stops the task-running loop.

It helps validate a PRP task file, run tasks sequentially or in parallel, choose a model, check progress, and stop the loop when needed.

It removes the need to launch and track each planned task manually while keeping progress and activity available for review.

prp-run — Skill for Claude Code and Codex by OZmasterAI: A task runner for a PRP, a written implementation…

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/ozmasterai/torus-framework/prp-run

Any agent

npx skills add OZmasterAI/Torus-Framework --skill prp-run

Clone the repo

git clone --depth 1 https://github.com/OZmasterAI/Torus-Framework

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ozmasterai/torus-framework/prp-run.svg)](https://agentmods.dev/skills/ozmasterai/torus-framework/prp-run)

Your own site

<a href="https://agentmods.dev/skills/ozmasterai/torus-framework/prp-run"><img src="https://agentmods.dev/badge/skills/ozmasterai/torus-framework/prp-run.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 703 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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	$0.00000	$0.00703
Opus 5	$0.00000	$0.00351
Sonnet 5	$0.00000	$0.00141
Haiku 4.5	$0.00000	$0.00070

Measured 3d ago against content hash 2d87c3873990, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

prp-run scanned grade B with 1 finding 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 3d ago.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

4. **REPORT**: Show PID and how to monitor: `tail -f ~/.claude/PRPs/{prp-name}.loop.log`

dormant/skills/prp-run/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/prp-run — Sequential PRP Task Runner

When to use

When user says "prp run", "run prp", "run tasks", or wants to execute a PRP's tasks via fresh Claude instances for maximum reasoning quality.

Commands

/loop start <prp-name> [--max-iterations N] [--model sonnet|opus] [--parallel] — Start the orchestrator
/loop status <prp-name> — Show current task progress and activity log
/loop stop <prp-name> — Signal the loop to stop after current task

Start Flow

VALIDATE: Check ~/.claude/PRPs/{prp-name}.tasks.json exists
CONFIRM: Show task count and ask user to confirm 2.5. PARALLEL CHECK: If --parallel flag, use nohup python3 ~/.claude/scripts/torus-wave.py {prp-name} [flags] > ~/.claude/PRPs/{prp-name}.loop.log 2>&1 & instead of torus-loop.sh
LAUNCH: Run nohup ~/.claude/scripts/torus-loop.sh {prp-name} [flags] > ~/.claude/PRPs/{prp-name}.loop.log 2>&1 &
REPORT: Show PID and how to monitor: tail -f ~/.claude/PRPs/{prp-name}.loop.log

Status Flow

TASKS: Run python3 ~/.claude/PRPs/task_manager.py status {prp-name} and display results
ACTIVITY: Read ~/.claude/PRPs/{prp-name}.activity.md and show recent iterations
PROCESS: Check if loop is still running via pgrep -f "torus-loop.sh {prp-name}"

Stop Flow

SENTINEL: Create ~/.claude/PRPs/{prp-name}.stop (loop checks each iteration)
CONFIRM: Tell user the loop will stop after the current task completes
NOTE: For immediate stop, user can kill $(pgrep -f "torus-loop.sh {prp-name}")

Post-Completion Verification

When all tasks are done (or loop ends), run phase verification:

python3 ~/.claude/scripts/prp-phase-verify.py <prp-name> --auto-fix
If failures found → fix tasks are auto-added to tasks.json → restart loop to process them
If all pass → phase is verified, proceed to next phase or report completion

Rules

ALWAYS validate tasks.json exists before starting
NEVER start a loop if one is already running for the same PRP
Default model is sonnet (cost-effective); use opus only when user requests it
Default max iterations is 50
The loop runs OUTSIDE Claude Code — it spawns fresh instances via claude -p
Each instance gets full Memory MCP access via boot.py session start
Each successful task is git-committed automatically
Wave mode (--parallel) checks file overlap between tasks — tasks sharing files are never co-waved
ALWAYS run phase verification after loop completes before declaring success

Read the full file on GitHub · 45 lines

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.

3d ago First seen · 45 lines · 0 tokens per session scan B 2d87c3873990

Subscribe to this mod's changes

prp-run is a skill published in the GitHub repository OZmasterAI/Torus-Framework (5 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 703 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents 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

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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

prp-run