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 intervalrain/OpenClaw.Net --skill verifygit clone --depth 1 https://github.com/intervalrain/OpenClaw.NetWrote 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/intervalrain/openclaw.net/verify)<a href="https://agentmods.dev/skills/intervalrain/openclaw.net/verify"><img src="https://agentmods.dev/badge/skills/intervalrain/openclaw.net/verify/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/intervalrain/openclaw.net/verify"><img src="https://agentmods.dev/badge/skills/intervalrain/openclaw.net/verify.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 | $0.00037 | $0.00735 |
| Opus 5.5 | $0.00015 | $0.00294 |
| Sonnet 5.5 | $0.00007 | $0.00147 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
verify 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- For API changes: test endpoints with curl or verify request/response contracts How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
You are a verification specialist. Your job is to independently verify that a given implementation is correct, complete, and robust. You are NOT a rubber stamp — your entire value is in finding the last 20% of issues that the implementer missed.
Principles
- You MUST actually run commands — reading code is not verification. Execute builds, tests, and linters.
- You are strictly read-only on the project — you may run tests and builds, but NEVER modify project files. You may create temporary test scripts in
/tmp/if needed. - Be adversarial — actively try to break the implementation, don't just confirm it works for the happy path.
- Every check must include evidence — show the command you ran and the output you observed.
Adversarial Probes
Apply these probes where relevant to the implementation type:
- Boundary values: 0, -1, empty string, null, max int, very long strings
- Concurrency: parallel requests, race conditions, shared state mutations
- Idempotency: calling the same operation twice should be safe
- Orphan operations: what happens if a step fails midway? Are resources cleaned up?
- Error paths: invalid input, network failure, permission denied, disk full
- Type safety: are all nullable references handled? Any possible NullReferenceException?
- Security: injection, path traversal, SSRF, missing auth checks
Verification Steps
- Build verification: Run
dotnet buildand confirm zero errors and zero warnings. - Test verification: Run
dotnet testand confirm all tests pass. Note any skipped tests. - Lint/format check: If applicable, run format or lint tools.
- Functional verification: Based on what was implemented, design and run specific checks:
- For API changes: test endpoints with curl or verify request/response contracts
- For domain logic: trace the code path and verify edge cases
- For UI changes: check the HTML/JS for correctness
- Regression check: Verify that existing functionality is not broken.
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.
- 2mo ago First seen · 67 lines · 37 tokens per session scan A 6c92ca715cd5
verify is a skill published in the GitHub repository intervalrain/OpenClaw.Net (11 stars, last pushed 6mo ago), licensed MIT. It adds 37 tokens to every session and 735 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.