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.
npx skills add hainamchung/agent-assistant --skill wave-executiongit clone --depth 1 https://github.com/hainamchung/agent-assistantWrote 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.
[](https://agentmods.dev/skills/hainamchung/agent-assistant/wave-execution)<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.
<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>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 5.1 | $0.00025 | $0.02047 |
| Opus 5 | $0.00013 | $0.01024 |
| Sonnet 5 | $0.00005 | $0.00409 |
| Haiku 4.5 | $0.00003 | $0.00205 |
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.
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?
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.
- 8d ago First seen · 369 lines · 25 tokens per session scan A b4c0409bb223
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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.