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-at-completeness-checkgit 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-at-completeness-check)<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-at-completeness-check"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-at-completeness-check/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-at-completeness-check"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-at-completeness-check.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 | $0.00046 | $0.03728 |
| Opus 5 | $0.00023 | $0.01864 |
| Sonnet 5 | $0.00009 | $0.00746 |
| Haiku 4.5 | $0.00005 | $0.00373 |
Grade A, and why
nw-at-completeness-check 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 10d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AT Completeness Check — Canonical Taxonomy
Mechanical gate for acceptance-test completeness. Runs against any candidate AT set. Each unchecked item = potential gap. Verdict deterministic by count, not judgment.
Provenance: research-anchored 7-category taxonomy, paradigm-neutral. See docs/research/at-edge-case-taxonomy-2026-05-19.md for full literature review.
Anchors [1]-[14] reference research doc bibliography.
Domain extensions
Project-specific AT-class specializations live as YAML overlays in domain-extensions/ (sibling dir to this SKILL.md). The canonical 7-category taxonomy stays paradigm-neutral; domain overlays add extra_checks that the reviewer appends to the 15-item checklist for features opting in.
When to add an extension: project surfaces an AT-class that is a specialization of one or more canonical categories (typically C5 + C6) but not a new general category. Example: nWave IP/Privacy boundary = public:false mode flag (C5) + leak-in-output failure-contract (C6) — lives in domain-extensions/nwave-installer.yaml, NOT in canonical taxonomy.
Overlay schema (domain-extensions/<kebab-case-domain-id>.yaml):
name: <kebab-case-domain-id>
version: <semver>
applies_to: <project / package / feature-pattern>
extends_canonical: [C5, C6] # which canonical categories this specializes
extra_checks:
- id: <DomainID>a
description: <what to verify>
maps_to_canonical: C6
mandatory: <bool>
Opt-in per feature — in docs/feature/{id}/distill/at-completeness-extensions.yaml:
extensions: [nwave-installer]
Reviewer adds overlay's extra_checks to the canonical 15-item checklist for that feature only. Verdict thresholds scale with total item count.
1. Canonical 7-category taxonomy (paradigm-neutral)
| ID | Category | Anchor | One-line definition |
|---|---|---|---|
| C1 | Equivalence & Boundary | ISTQB §4.2 [1] / Beizer ch.5 [2] | Partition input domain + test at/adjacent to each boundary |
| C2 | State & Transition | ISTQB §4.2.4 [1] / Hendrickson [3] / Hypothesis stateful [4] | Every legal transition + illegal-event-from-each-state + self-loops/terminal exits |
| C3 | Count Cardinality (0/1/N) | Hendrickson "Count" [3] / Adzic key examples [5] | Empty / singleton / many for every collection input or output |
| C4 | CRUD-Lifecycle & Idempotency | Hendrickson "CRUD" [3] / Hillel Wayne PBT+Contracts [6] | Repeat / replay / out-of-order ops preserve invariants; f(f(x)) == f(x) for idempotent ops |
| C5 | Mode-Flag / Decision-Table | ISTQB §4.2.3 [1] / Adzic "key examples" [7] | Every materially-distinct Cartesian combination of mode flags exercised |
| C6 | Negative & Robustness (Postel) | RFC 760 §1.2.10 [8] / FEW HICCUPPS [9] / Kaner LLST [10] / RIMGEA [11] | Hostile/degenerate input → explicit typed-error contract, never silent coercion |
| C7 | Configuration / Environment / Interruption | Bach HTSM SFDIPOT [12] / Hendrickson "Configurations+Interruptions+Starvation" [3] / Marick Q4 [13] | Resource starvation + interruption mid-flow + concurrent actors |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 270 lines · 46 tokens per session scan A 0cf9229d5528
nw-at-completeness-check is a skill published in the GitHub repository nWave-ai/nWave (610 stars, last pushed 4d ago), licensed MIT. It adds 46 tokens to every session and 3,728 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.
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
moai-workflow-tdd
Test-Driven Development workflow specialist using RED-GREEN-REFACTOR cycle for test-first software development. Use when developing new features from scratch or when behavior specification drives implementation.
tdd-enforcement
Red-Green-Refactor TDD methodology with mandatory failing tests, minimal implementation, quality refactoring, and 80% coverage gating.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.