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 nWave-ai/nWave --skill nw-buddy-wave-knowledgegit clone --depth 1 https://github.com/nWave-ai/nWaveWrote 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/nwave-ai/nwave/nw-buddy-wave-knowledge)<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-buddy-wave-knowledge"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-buddy-wave-knowledge/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/nwave-ai/nwave/nw-buddy-wave-knowledge"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-buddy-wave-knowledge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.01895 |
| Opus 5 | $0.00015 | $0.00948 |
| Sonnet 5 | $0.00006 | $0.00379 |
| Haiku 4.5 | $0.00003 | $0.00189 |
Grade A, and why
nw-buddy-wave-knowledge 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 9d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wave Methodology Knowledge
The nWave methodology organizes work into a canonical sequence of waves. Each wave has a purpose, a primary agent, inputs from earlier waves, and outputs consumed by later waves. The buddy agent uses this map to answer "where am I in the process" and "what should I do next" questions without stepping into execution territory.
The canonical wave sequence
DISCOVER -> DISCUSS -> SPIKE(opt) -> DESIGN -> DEVOPS -> DISTILL -> DELIVER
Each wave has a slash command (/nw-<wave>) and a primary agent. Waves run top-to-bottom. Skipping waves is a smell; going back to revise an earlier wave is normal and expected. SPIKE is optional — include it when validating a new mechanism, performance requirement, or external integration.
Wave-by-wave reference
1. DISCOVER
- Purpose: validate that an opportunity exists and is worth pursuing.
- Primary agent: product-discoverer.
- Inputs: a rough idea, a user complaint, a market signal, or a strategic prompt.
- Outputs: an evidence brief — problem statement, target users, pains, existing solutions, strength of signal, go/no-go recommendation.
- Typical artifacts:
docs/discover/<opportunity>-brief.md, user interview notes, competitive scans. - Common questions: "is this worth doing?", "who has this problem?", "what's the evidence?"
2. DISCUSS
- Purpose: turn a validated opportunity into user stories with acceptance criteria.
- Primary agent: product-owner.
- Inputs: DISCOVER output — validated problem and target users.
- Outputs: a set of user stories, each with a goal, acceptance criteria in Given-When-Then form, and a rough priority.
- Typical artifacts:
docs/discuss/<feature>-stories.md, a backlog update. - Common questions: "what does 'done' look like for this feature?", "what are the user stories?"
3. SPIKE (optional)
- Purpose: validate one core assumption through timeboxed throwaway code before investing in architecture design.
- Primary agent: software-crafter.
- Inputs: DISCUSS output — stories, acceptance criteria, and assumptions to test.
- Outputs: spike findings documenting what works, what assumptions were wrong, performance measurements. Code is discarded.
- Typical artifacts:
docs/feature/<name>/spike/findings.md, throwaway code (not committed). - Common questions: "will this mechanism work?", "can we hit the performance budget?", "does the third-party API behave as expected?"
- When to run: Include SPIKE when the feature involves a new mechanism never tried before, a performance requirement that can't be validated by reasoning alone, or an external integration with unknown behavior. Skip for pure refactoring, bug fixes, or features < 1 day.
- Duration: max 1 hour, timeboxed.
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.
- 9d ago First seen · 136 lines · 31 tokens per session scan A f77a68831223
nw-buddy-wave-knowledge is a skill published in the GitHub repository nWave-ai/nWave (610 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 1,895 once invoked, about $0.0002 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.
Other skills, from other repositories
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
engineering-workflow
A Chinese-language workflow for reliable software development. It describes exploring the problem, making a plan, using TDD (test-driven development, where tests are written before the code), debugging methodically, reviewing code, and verifying the result.
test-driven-development
Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.
tdd-enforcement
Red-Green-Refactor TDD methodology with mandatory failing tests, minimal implementation, quality refactoring, and 80% coverage gating.
story-development
Implement user stories with test-driven development methodology.
tdd
A Test-Driven Development guide. TDD means writing a failing test first, adding the smallest implementation that passes it, and then improving the code while keeping the tests passing.