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-review-output-formatgit 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-review-output-format)<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-review-output-format"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-review-output-format/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-review-output-format"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-review-output-format.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 | $0.00023 | $0.00556 |
| Opus 5.5 | $0.00009 | $0.00222 |
| Sonnet 5.5 | $0.00005 | $0.00111 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
nw-review-output-format 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 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.
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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Platform Review Output Format
YAML Structure
review_id: "platform_rev_{timestamp}"
reviewer: "nw-platform-architect-reviewer (Atlas)"
artifact_reviewed: "{path to platform design documents}"
review_date: "{ISO 8601 timestamp}"
external_validity_check:
deployment_path_complete: "{PASS/FAIL}"
observability_enabled: "{PASS/FAIL}"
rollback_capability: "{PASS/FAIL}"
security_gates_present: "{PASS/FAIL}"
overall_status: "{PASS/FAIL/BLOCKER}"
blocking_issues:
- "{issue description if any}"
strengths:
- category: "{pipeline/infrastructure/deployment/observability/security}"
description: "{what is done well}"
evidence: "{specific example from design}"
issues_identified:
- id: 1
category: "{pipeline/infrastructure/deployment/observability/security}"
dimension: "{critique dimension name}"
severity: "{blocker/critical/high/medium/low}"
description: "{clear description}"
impact: "{consequence if not addressed}"
recommendation: "{specific, actionable fix}"
evidence: "{where in the design this was found}"
dora_metrics_assessment:
deployment_frequency_enabled: "{yes/no/partial}"
lead_time_achievable: "{yes/no/partial}"
change_failure_rate_trackable: "{yes/no/partial}"
time_to_restore_measurable: "{yes/no/partial}"
assessment_notes: "{specific observations}"
priority_validation:
largest_bottleneck_addressed: "{YES/NO/UNCLEAR}"
simple_alternatives_documented: "{ADEQUATE/INADEQUATE/MISSING}"
constraint_prioritization: "{CORRECT/INVERTED/NOT_ANALYZED}"
verdict: "{PASS/FAIL}"
recommendations:
immediate:
- "{must fix before approval}"
short_term:
- "{should fix soon}"
long_term:
- "{consider for future improvement}"
approval_status: "{approved/rejected_pending_revisions/conditionally_approved}"
conditions_for_approval:
- "{condition if conditionally_approved}"
Approval Criteria
Approved: No blocker or critical issues. High issues acknowledged with timeline.
Conditionally approved: No blockers. Critical issues have mitigation plan. High issues documented for follow-up.
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 · 75 lines · 23 tokens per session scan A 81ceeb5b241e
nw-review-output-format is a skill published in the GitHub repository nWave-ai/nWave (620 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 556 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
orchestrated-execution
Execute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.
Pair Programming
AI-assisted pair programming with multiple modes (driver$navigator$switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…
team-implement
Use for executing implementation plans only on explicit request. Never infer from a ready plan. Implements and verifies slices.
prune
Run all quality lenses (validate, simplify), aggregate findings into a design doc, then drive the full feature chain (PRD → TDD → PR) to fix them systematically.
ai-agents-validation-and-qa
What counts as evidence in ai-agents and how to produce it. Covers the TESTING-RIGOR pos+neg+edge bar, test layout and collection reality, coverage proof commands, runtime-contract tests with negative controls, and ADR-034 QA skip semantics at session end. Use when you say what counts as evidence, how do I test this…
Pair Programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…