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-tlaplus-verificationgit 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-tlaplus-verification)<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-tlaplus-verification"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-tlaplus-verification/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-tlaplus-verification"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-tlaplus-verification.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 | $0.00020 | $0.01706 |
| Opus 5 | $0.00010 | $0.00853 |
| Sonnet 5 | $0.00004 | $0.00341 |
| Haiku 4.5 | $0.00002 | $0.00171 |
Grade A, and why
nw-tlaplus-verification 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 3d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TLA+ / Formal Verification
When and how to use TLA+ for design verification. Complements PBT (which verifies implementation).
Decision Tree: When to Use TLA+ vs PBT vs Both
Is the risk in the DESIGN or the IMPLEMENTATION?
|
+-- Design risk (protocol correctness, distributed coordination, concurrency)
| -> Does the system involve concurrent or distributed state?
| Yes -> Use TLA+ for design verification
| Then use PBT to verify implementation matches design
| No -> PBT alone is likely sufficient
|
+-- Implementation risk (edge cases, serialization, data transforms)
| -> Use PBT alone
|
+-- Both
-> TLA+ validates design, PBT validates implementation
Use TLA+ When:
- Design bug would cause data loss or significant customer impact
- System involves concurrent or distributed state manipulation
- Subtle interactions between components are hard to reason about informally
- Informal reasoning or testing has already failed to prevent bugs
Skip TLA+ When:
- Simple CRUD with straightforward business logic
- UI/UX behavior
- Performance optimization (TLA+ models correctness, not performance)
- Design is well-understood; risk is only in implementation bugs
- Rapid prototyping where design changes frequently
TLA+ in 60 Seconds
TLA+ describes what a system should do, not how. A specification consists of:
- Variables: State components
- Init: Valid starting states
- Next: How system transitions between states
- Invariants: Conditions that must hold in every reachable state
TLC model checker exhaustively explores all reachable states within bounded model. If invariant violated, TLC provides counterexample trace -- shortest path from initial state to violation.
PlusCal as Entry Point
PlusCal is imperative-looking language transpiling to TLA+. Most programmers find it easier to learn first.
(* --algorithm Transfer
variables accounts = [a |-> 100, b |-> 100];
process Transfer \in 1..2
variables from, to, amount;
begin
Pick:
from := "a"; to := "b"; amount := 50;
Check:
if accounts[from] >= amount then
Debit:
accounts[from] := accounts[from] - amount;
Credit:
accounts[to] := accounts[to] + amount;
end if;
end process;
end algorithm; *)
\* Invariant: total money is conserved
MoneyConserved == accounts["a"] + accounts["b"] = 200
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.
- 3d ago First seen · 193 lines · 20 tokens per session scan A b229f4b45f70
nw-tlaplus-verification is a skill published in the GitHub repository nWave-ai/nWave (610 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 1,706 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 2026-09-06.
Other skills, from other repositories
i4h-catheter-navigation-e2e
End-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the v0.7 pipeline.
i4h-catheter-navigation-render-drr
Render a single DRR fluoroscopy frame from a CT cache or synthetic phantom. Use when asked to render DRR, generate a fluoro image, or smoke-test the Slang renderer.
i4h-catheter-navigation-smoke
Run CPU-only fluorosim smoke tests (imports, preprocessing, CLI parsers). Use when asked to smoke-test catheter navigation in CI or without a GPU.
precision-bio-tests
Expert guide for testing bioinformatics MCP servers. Covers pytest, DRYRUN modes, and PatientOne simulation scenarios.
ras-end-to-end
Standard operating procedure for an auditable, headless HEC-RAS workflow via the hec-ras MCP server — how to plan, copy, edit boundaries, run, QA-gate, read results, compare, plot, audit, and safely stop. Use FIRST whenever an agent is handed a HEC-RAS project (.prj folder) or a results file (.p##.hdf) plus a…
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.