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 agentmods add skills/ai-swiss/base/verifynpx skills add ai-swiss/base --skill verifygit clone --depth 1 https://github.com/ai-swiss/baseWrote 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/ai-swiss/base/verify)<a href="https://agentmods.dev/skills/ai-swiss/base/verify"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/verify.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.00623 |
| Opus 5 | $0.00018 | $0.00311 |
| Sonnet 5 | $0.00007 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
verify 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.
What it actually says
Verify the gates
The discipline is gate-enforced, not trusted. A contributor runs the gates locally before CI does. The single command runs them all; run it and read the output honestly.
Steps
- Run the core gates:
npm run check(tests, typecheck, thespec:checkchain, docs validation and route-test). Green here means the core is sound; CI additionally runs coverage, the regenerated-artifact diffs (base index/base build),doctor, the pack smoke test and the MCP/Studio suites — run those when you touch those areas (commands inCONTRIBUTING.md). - Read each gate's meaning if one fails (the full registry is
docs/reference/gates.md; each script also prints what it checks): the requirements matrix rejects phantom citations;spec-syncwants a runtime change to touchspecs/or declare[SPEC-NEUTRAL]; the immutability check forbids renumbering or reusing an ID;changelog-syncwants a visible change to carry its[Unreleased]line. - Fix the cause, not the symptom. Never bypass a hook (
--no-verify,--force), never add a silent fallback to make a gate pass. A red gate is information. - Confirm the proof is honest. Regenerate the matrix (
npm run spec:matrix) and check that the change's requirements are✅, not⚠️/❌; a gap is reported, never hidden. - Report green (or the exact failing gate and why), then hand back for commit.
What you never do
- Declare done on a red gate, or claim a gate passed without running it.
- Run heavy suites to look thorough; run what can falsify the change, plus the one command.
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 · 52 lines · 37 tokens per session scan A 606a4bdcf8a0
verify is a skill published in the GitHub repository ai-swiss/base (42 stars, last pushed 20d ago), licensed Apache-2.0. It adds 37 tokens to every session and 623 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
agt-policy-authoring
Create and validate a minimal AGT Copilot CLI policy tailored to the repository being inspected.
silicon-throne
硅基圣座总控核心，以神谕式统御把零散任务压成 末将-first 之文明工程.
digital-native-governance-check
Assess Azure governance maturity for Digital Natives and startups. Detects the most common anti-patterns from the "Digital Natives on Azure" series: incomplete Service Health alerts, flat subscription topology without Management Groups, excessive RBAC (everyone is Owner), missing budget alerts, no Managed Identity…
intelligence-engineer
VNX-specific domain expertise for the intelligence system, central state databases, and dispatch lifecycle. Use when working on qualityintelligence.db / runtimecoordination.db / dispatchtracker.db, codesnippets FTS5, snippetmetadata linkage, successpatterns / antipatterns, T0 state projection (t0state.json)…
finops-intelligence
Comprehensive FinOps analysis combining cost optimization, waste identification, and chargeback reporting. Use when asked about reducing Azure spend, finding unused resources, cost per team, chargeback, showback, cost anomalies, rightsizing, or monthly cost review.
capacity-planning
Assess Azure resource capacity, quota utilization, and growth trends to prevent outages from resource exhaustion. Use when asked about capacity, quotas, scaling readiness, load testing prep, Black Friday readiness, or growth projections.