agentmods.dev

base: Skill for Claude Code

.ai/agents/base-contributor/skills/processes/verify/SKILL.md

verify is a skill for Claude Code from ai-swiss/base. It costs 37 tokens per session (623 once invoked), scanned A, original, Apache-2.0.

A verification skill for running a project's required quality checks before committing or pushing changes. It checks items such as tests, type checking, documentation, and project-specific rules.

In plain words
What is it for?
Use it to run the project's verification gates, understand failures, regenerate required reports, and confirm that the evidence for a change is honest.
Why use it?
It helps catch broken code, missing documentation updates, invalid requirement references, and other issues before CI or reviewers find them.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is ai-swiss/base's own configuration. It tells Claude Code how to work on base itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything base configures →

not rated 65repo +1 8d ago A scan SkillSpector: pass 37 tokens original Apache-2.0
View source ↗ ai-swiss/base a-i.swiss
Reuse

Borrowing it

Nothing to install: this file belongs to ai-swiss/base. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ai-swiss/base/main/.ai/agents/base-contributor/skills/processes/verify/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ai-swiss/base

Made for: Claude Code.

Wrote 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.

agentmods badge for verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-swiss/base/verify/github.svg)](https://agentmods.dev/skills/ai-swiss/base/verify)
Your own site
<a href="https://agentmods.dev/skills/ai-swiss/base/verify"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/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.

agentmods 80×15 button for verify

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai-swiss/base/verify"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 623 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.00623
Opus 5.5 $0.00015 $0.00249
Sonnet 5.5 $0.00007 $0.00125
Haiku 4.5 $0.00004 $0.00062

Measured 2mo ago against content hash 606a4bdcf8a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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.

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.

.ai/agents/base-contributor/skills/processes/verify/SKILL.md · 52 lines

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

  1. Run the core gates: npm run check (tests, typecheck, the spec:check chain, 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 in CONTRIBUTING.md).
  2. 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-sync wants a runtime change to touch specs/ or declare [SPEC-NEUTRAL]; the immutability check forbids renumbering or reusing an ID; changelog-sync wants a visible change to carry its [Unreleased] line.
  3. 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.
  4. 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.
  5. 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.
Changes

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.

  1. 2mo ago First seen · 52 lines · 37 tokens per session scan A 606a4bdcf8a0

Subscribe to this mod's changes

verify is a skill published in the GitHub repository ai-swiss/base (65 stars, last pushed 8d ago), licensed Apache-2.0. It adds 37 tokens to every session and 623 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.

Testingaiai-agentsclicognitive-sovereigntydigital-sovereigntygovernance
Related

verify compared with skills from other repositories

verify next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
verifyai-swiss/baseSkill658d agoApache-2.0A37Claude Code
complianceericrisco/rsc-harnessSkill5032d agoMITA96Claude Code, Codex
wallet-cliBofAI/skillsSkill1644d agoMITA92Codex
vaultjoelhooks/joelclawSkill65yesterdaynoneA82Claude Code
feishuHmbown/CodeWhaleSkill41k5d agoMITA33Claude Code, Codex
interviewHmbown/CodeWhaleSkill41k5d agoMITA40Claude Code, Codex
atmos-validationcloudposse/atmosSkill1.4kyesterdayApache-2.0A31Claude Code