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-security-by-designgit 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-security-by-design)<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-security-by-design"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-security-by-design/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-security-by-design"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-security-by-design.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 | $0.00037 | $0.02203 |
| Opus 5.5 | $0.00015 | $0.00881 |
| Sonnet 5.5 | $0.00007 | $0.00441 |
| Haiku 4.5 | $0.00004 | $0.00220 |
Grade A, and why
nw-security-by-design scanned grade A 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 1mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| Command Injection | `os.system(f"cmd {input}")` | `subprocess.run(["cmd", input], shell=False)` | 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.
Security by Design
OWASP Security Design Principles
Apply these during design -- retrofitting security is 10-100x more expensive.
| # | Principle | Architect Action |
|---|---|---|
| 1 | Security by Design | Include security requirements in architecture documents |
| 2 | Security by Default | Ship restrictive defaults; require explicit opt-in for relaxed settings |
| 3 | Defense in Depth | Layer controls: WAF + input validation + output encoding + parameterized queries |
| 4 | Fail Secure | Deny access on error; closed-by-default network policies |
| 5 | Least Privilege | Scoped service accounts; time-limited tokens; minimum permissions |
| 6 | Compartmentalize | Network segmentation; separate databases per trust level |
| 7 | Separation of Duties | Separate deployment approval from code authorship |
| 8 | Economy of Mechanism | Minimize attack surface; simple, auditable security code |
| 9 | Complete Mediation | Check authorization on every request; no cached auth decisions |
| 10 | Open Design | Use published, peer-reviewed algorithms; no security-through-obscurity |
| 11 | Least Common Mechanism | Separate admin and user interfaces |
| 12 | Psychological Acceptability | Make the secure path the easy path; minimize user friction |
STRIDE Threat Modeling
Apply STRIDE to every component in a Data Flow Diagram (DFD). Four questions drive every session:
- What are we working on? (system model)
- What can go wrong? (threat identification)
- What are we going to do about it? (mitigation)
- Did we do a good enough job? (review)
STRIDE Reference
| Threat | Violated Property | Architectural Mitigation |
|---|---|---|
| Spoofing | Authentication | MFA, mutual TLS, certificate pinning, OAuth2+PKCE |
| Tampering | Integrity | Input validation, HMAC, parameterized queries, immutable infra |
| Repudiation | Non-repudiation | Tamper-evident logging (append-only), digital signatures, SIEM |
| Info Disclosure | Confidentiality | Encryption at rest+transit, least privilege, generic error messages |
| Denial of Service | Availability | Rate limiting, circuit breakers, auto-scaling, query complexity limits |
| Elevation of Privilege | Authorization | Least privilege, RBAC/ABAC, signed tokens verified server-side |
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.
- 1mo ago First seen · 202 lines · 37 tokens per session scan A 62bb8bf1da2e
nw-security-by-design is a skill published in the GitHub repository nWave-ai/nWave (620 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 2,203 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other skills, from other repositories
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.
tdd
Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.
moai-run
Implement SPEC requirements using DDD/TDD methodology.
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.