wave-execution

wave-execution is a skill for Claude Code, Codex from hainamchung/agent-assistant. It costs 25 tokens per session (2,047 once invoked), scanned A, original, MIT.

A method for running independent implementation tasks in parallel groups while respecting their dependencies. A dependency is a task that must finish before another task can start.

In plain words
What is it for?
Use it to organise multi-step development work into execution waves based on which tasks depend on others.
Why use it?
It reduces waiting time in plans where some tasks can proceed at the same time and others must follow a specific order.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to organise multi-step development work into execution waves based on which tasks depend on others.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hainamchung/agent-assistant/wave-execution
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.

Any agent
npx skills add hainamchung/agent-assistant --skill wave-execution
Clone the repo
git clone --depth 1 https://github.com/hainamchung/agent-assistant

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.

agentmods badge for wave-execution

README.md
[![agentmods](https://agentmods.dev/badge/skills/hainamchung/agent-assistant/wave-execution/github.svg)](https://agentmods.dev/skills/hainamchung/agent-assistant/wave-execution)
Your own site
<a href="https://agentmods.dev/skills/hainamchung/agent-assistant/wave-execution"><img src="https://agentmods.dev/badge/skills/hainamchung/agent-assistant/wave-execution/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for wave-execution

Your own site · 80×15
<a href="https://agentmods.dev/skills/hainamchung/agent-assistant/wave-execution"><img src="https://agentmods.dev/badge/skills/hainamchung/agent-assistant/wave-execution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,047 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00025 $0.02047
Opus 5 $0.00013 $0.01024
Sonnet 5 $0.00005 $0.00409
Haiku 4.5 $0.00003 $0.00205

Measured 8d ago against content hash b4c0409bb223, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

wave-execution 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 8d 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.

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.

skills/wave-execution/SKILL.md · 369 lines

How it starts

The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wave-Based Parallel Execution

Problem: Sequential execution wastes time on independent tasks.

Solution: Group tasks into waves based on dependencies. Execute waves sequentially, tasks within waves in parallel.


When to Use

Multiple tasks in implementation plan?
        ↓ YES
WAVE EXECUTION ← APPLY

Use when:

  • 2+ independent tasks in implementation plan
  • Tasks have clear dependency relationships
  • Parallel execution provides clear speedup
  • Subagents available for parallel dispatch

Don't use when:

  • Single sequential task
  • Tasks deeply interdependent (must run sequentially)
  • No subagent dispatch capability
  • Time not critical (efficiency not priority)

Wave Resolution Algorithm

Dependency Analysis

## TASK DEPENDENCY MATRIX

Tasks:
T1: Create user model
T2: Create user API (depends on T1)
T3: Create auth API (depends on T1)
T4: Create checkout API (depends on T2, T3)
T5: Create payment API (depends on T4)
T6: Create email notification (depends on T2)

Dependency Graph:
T1 → [T2, T3]
T2 → [T4, T6]
T3 → [T4]
T4 → [T5]
T6 → []

Wave Classification

Wave Tasks Reason Parallel?
Wave 1 T1 No dependencies No (single task)
Wave 2 T2, T3 Depend only on T1 YES
Wave 3 T4, T6 Depend only on Wave 2 YES
Wave 4 T5 Depend on T4 No (single task)

Wave Resolution Output

## WAVE RESOLUTION

Wave 1 (Sequential):
└── T1: Create user model

Wave 2 (Parallel):
├── T2: Create user API
└── T3: Create auth API

Wave 3 (Parallel):
├── T4: Create checkout API
└── T6: Create email notification

Wave 4 (Sequential):
└── T5: Create payment API

Total: 6 tasks → 4 waves
Parallelization: 2.0x speedup (vs sequential)

Execution Protocol

Pre-Execution Checklist

□ All tasks identified and documented?
□ Dependencies mapped?
□ Wave boundaries determined?
□ File ownership assigned per task?
□ Parallel safety verified (no file conflicts)?
□ Sequential dependencies enforced?
□ Budget allocated per wave?
□ Verification checkpoints set?

Read the full file on GitHub · 369 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. 8d ago First seen · 369 lines · 25 tokens per session scan A b4c0409bb223

Subscribe to this mod's changes

wave-execution is a skill published in the GitHub repository hainamchung/agent-assistant (54 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 2,047 once invoked, about $0.0001 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 2026-09-03.