prp-wave

A task runner that executes the tasks in an implementation blueprint, called a PRP, in parallel groups called waves. It supports a controlled in-process mode and an external batch mode.

In plain words
What is it for?
Use it to start, monitor, or stop parallel execution of a PRP, and choose its model, wave limit, timeout, or execution mode.
Why use it?
It lets independent tasks run at the same time, shortening batch work while the default mode keeps quality checks active for each task.

Skill for Claude CodeCodex

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-wave
Any agent
npx skills add OZmasterAI/Torus-Framework --skill prp-wave
Clone the repo
git clone --depth 1 https://github.com/OZmasterAI/Torus-Framework

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,271 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02271
Opus 5 $0.00000 $0.01136
Sonnet 5 $0.00000 $0.00454
Haiku 4.5 $0.00000 $0.00227

Measured 2d ago against content hash 47c675ea6e4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

prp-wave 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 2d 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.

Show PID and how to monitor: `tail -f ~/.claude/PRPs/{prp}.wave.log`
dormant/skills/standalone/prp-wave/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/prp-wave — Parallel PRP Task Runner

When to use

When user says "prp wave", "parallel prp", "batch tasks", or wants to execute a PRP's tasks via parallel execution for maximum throughput.

Two modes:

  • In-Claude (default) — Claude orchestrates via Task tool subagents. All 16 gates active on executors. Best for gated safety.
  • External (--external) — Spawns torus-wave.py which launches claude -p processes. Zero gates on executors. Best for batch throughput.

Commands

  • /wave start <prp> [--model sonnet|opus] [--max-waves N] — In-Claude gated mode (default)
  • /wave start <prp> --external [--max-iterations N] [--model sonnet|opus] [--timeout SECONDS] — External ungated batch mode
  • /wave status <prp> — Show current task progress and activity log
  • /wave stop <prp> — Signal the wave to stop after current wave completes

In-Claude Start Flow (default)

1. VALIDATE

Check ~/.claude/PRPs/{prp}.tasks.json exists. If not, abort with error.

2. CONFIRM

Run python3 ~/.claude/PRPs/task_manager.py status {prp} to get task count. Show the user:

  • Total tasks, pending count, failed count
  • Mode: In-Claude (gated) — all 16 quality gates active
  • Model: sonnet (default) or opus if --model opus
  • Max waves: N (default 50) if --max-waves N

Ask user to confirm before proceeding.

3. CLEANUP

Run: python3 -c "import sys; sys.path.insert(0, '$HOME/.claude/hooks'); from shared.agent_channel import cleanup; cleanup(max_age_hours=24)"

3.5 PLAN VERIFICATION

Before spending executor tokens, validate the task plan structure. Run:

python3 ~/.claude/PRPs/task_manager.py plan-check {prp} ~/.claude/PRPs/{prp}.md

Parse the JSON output. Check:

  • uncovered — requirement IDs with no task covering them
  • orphan_tasks — tasks referencing nonexistent requirement IDs
  • pass — true if both lists are empty

If pass is false, show the user the gaps and ask whether to proceed anyway or abort.

Additionally, verify task file targets exist or are creatable:

python3 ~/.claude/PRPs/task_manager.py wave {prp}

For each task in the output, check that parent directories of all files entries exist. If any are missing, warn the user before proceeding.

Read the full file on GitHub · 202 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.

  1. 2d ago First seen · 202 lines · 0 tokens per session scan B 47c675ea6e4b

Subscribe to this mod's changes

prp-wave 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 2,271 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.

Related

Other skills, from other repositories

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

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 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