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 Stunspot/nova-the-optimal-ai-mind --skill software-verificationgit clone --depth 1 https://github.com/Stunspot/nova-the-optimal-ai-mindWrote 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/stunspot/nova-the-optimal-ai-mind/software-verification)<a href="https://agentmods.dev/skills/stunspot/nova-the-optimal-ai-mind/software-verification"><img src="https://agentmods.dev/badge/skills/stunspot/nova-the-optimal-ai-mind/software-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/stunspot/nova-the-optimal-ai-mind/software-verification"><img src="https://agentmods.dev/badge/skills/stunspot/nova-the-optimal-ai-mind/software-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00017 | $0.03086 |
| Opus 5.5 | $0.00007 | $0.01234 |
| Sonnet 5.5 | $0.00003 | $0.00617 |
| Haiku 4.5 | $0.00002 | $0.00309 |
Grade A, and why
software-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 12d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
60 files 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.
- activation-examples.md 949 B
- agents/openai.yaml 302 B
- assets/ci/github-actions-node.yml 371 B
- assets/ci/github-actions-python.yml 416 B
- assets/schemas/finding.schema.json 940 B
- assets/schemas/metered-verification-plan.schema.json 2.2 KB
- assets/schemas/normalized-results.schema.json 1.2 KB
- assets/schemas/scenario.schema.json 1.1 KB
- assets/schemas/verification-manifest.schema.json 11 KB
- assets/templates/execution-record.json 261 B
- assets/templates/exploratory-charter.md 400 B
- assets/templates/failure-triage.md 462 B
- assets/templates/metered-verification-plan.json 788 B
- assets/templates/metered-verification-response.md 3.2 KB
- assets/templates/residual-risk-ledger.md 357 B
- assets/templates/risk-register.md 428 B
- assets/templates/traceability-matrix.md 314 B
- assets/templates/verification-brief.md 529 B
- assets/templates/verification-manifest.json 971 B
- assets/templates/verification-report.md 577 B
- examples/parser-edge-cases/demonstration.md 1.1 KB
- examples/parser-edge-cases/expected/execution-record.json 2.3 KB
- examples/parser-edge-cases/expected/normalized-results.json 488 B
- examples/parser-edge-cases/expected/test_parser.py 711 B runs code
- examples/parser-edge-cases/expected/verification-manifest.json 3.4 KB
- examples/parser-edge-cases/expected/verification-report.md 1.3 KB
- examples/parser-edge-cases/input/__init__.py 32 B runs code
- examples/parser-edge-cases/input/parser.py 424 B runs code
- examples/parser-edge-cases/walkthrough.md 622 B
- examples/pending-replacement/walkthrough.md 4.9 KB
- examples/python-regression/demonstration.md 1.1 KB
- examples/python-regression/expected/execution-record.json 1.6 KB
- examples/python-regression/expected/fix.patch 182 B
- examples/python-regression/expected/fixed/__init__.py 55 B runs code
- examples/python-regression/expected/fixed/reporting.py 245 B runs code
- examples/python-regression/expected/normalized-results.json 493 B
- examples/python-regression/expected/post-fix-execution-record.json 666 B
- examples/python-regression/expected/test_date_filter.py 724 B runs code
- examples/python-regression/expected/test_fixed_date_filter.py 699 B runs code
- examples/python-regression/expected/verification-manifest.json 3.0 KB
- examples/python-regression/expected/verification-report.md 1.2 KB
- examples/python-regression/input/__init__.py 35 B runs code
- examples/python-regression/input/reporting.py 297 B runs code
- examples/python-regression/input/test_existing.py 380 B runs code
- examples/python-regression/walkthrough.md 980 B
- examples/typescript-api-change/demonstration.md 1.5 KB
- examples/typescript-api-change/expected/cancelSubscription.integration.test.ts 1.6 KB runs code
- examples/typescript-api-change/expected/verification-manifest.json 4.3 KB
- examples/typescript-api-change/expected/verification-report.md 1.5 KB
- examples/typescript-api-change/input/package.json 190 B
- examples/typescript-api-change/input/requirement.md 318 B
- examples/typescript-api-change/input/src/subscriptionService.ts 1.2 KB runs code
- examples/typescript-api-change/input/tests/cancelSubscription.test.ts 674 B runs code
- examples/typescript-api-change/walkthrough.md 936 B
- fallback/intake-card.md 543 B
- fallback/master-prompt.md 7.4 KB
- fallback/output-templates.md 785 B
- fallback/review-prompt.md 2.1 KB
- output-contract.md 1.9 KB
- references/core/boundary-and-equivalence.md 955 B
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.
- 12d ago Changed · +4 lines · +3 tokens per session dd56282bac22
- 1mo ago Changed · +1 lines 8ba1812ae361
- 1mo ago Changed · -18 lines b1e0730a00ce
- 1mo ago First seen · 124 lines · 14 tokens per session scan A 7fee2d5c158f
software-verification is a skill published in the GitHub repository Stunspot/nova-the-optimal-ai-mind (29 stars, last pushed 2d ago), with no licence file. It adds 17 tokens to every session and 3,086 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 2026-08-30.
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.
playwright-qa
Automated visual QA testing using Playwright — navigate web apps like a real user, capture screenshots, find bugs, and fix them.
write-tests
Generate unit tests for existing code.
run-wenlan-app
Build, launch, screenshot, and drive the wenlan-app Tauri desktop app in dev mode on macOS (WKWebView) or Windows (WebView2). Use when asked to run or start the app, verify a UI change in the real running app (not just tests), or take a screenshot of it.
taste
Use when implementing any feature, bugfix, or behavior change, before writing the implementation code. Especially use under pressure - production is down, "just make it work", "quick fix" - which is when it gets skipped.
e2e-testing
ORGII keeps two separate E2E surfaces. Do not use one as proof for the other.