agentmods.dev

baerly-storage: Skill for Claude Code

.claude/skills/verification/SKILL.md

verification is a skill for Claude Code from Gusto/baerly-storage. It costs 87 tokens per session (448 once invoked), scanned A, original, Apache-2.0.

A reference guide to every verification, test, fuzzing, benchmarking, and operator command in a code repository. It also explains which checks need services such as Minio, Postgres, or valid credentials.

In plain words
What is it for?
Use it to find the right command for a less common check, understand why a test is skipped, or run repository benchmarks and administrative checks.
Why use it?
It fills in the commands and test requirements that a shorter project guide may not cover. It helps explain skipped tests and avoids commands that use stale build output.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is Gusto/baerly-storage's own configuration. It tells Claude Code how to work on baerly-storage 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 baerly-storage configures →

not rated 25repo today A scan 87 tokens original Apache-2.0
View source ↗ Gusto/baerly-storage medium.com
Reuse

Borrowing it

Nothing to install: this file belongs to Gusto/baerly-storage. 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/Gusto/baerly-storage/main/.claude/skills/verification/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Gusto/baerly-storage

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 verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/gusto/baerly-storage/verification/github.svg)](https://agentmods.dev/skills/gusto/baerly-storage/verification)
Your own site
<a href="https://agentmods.dev/skills/gusto/baerly-storage/verification"><img src="https://agentmods.dev/badge/skills/gusto/baerly-storage/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.

agentmods 80×15 button for verification

Your own site · 80×15
<a href="https://agentmods.dev/skills/gusto/baerly-storage/verification"><img src="https://agentmods.dev/badge/skills/gusto/baerly-storage/verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 448 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.
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 $0.00087 $0.00448
Opus 5.5 $0.00035 $0.00179
Sonnet 5.5 $0.00017 $0.00090
Haiku 4.5 $0.00009 $0.00045

Measured 2mo ago against content hash bac7276b81c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 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.

.claude/skills/verification/SKILL.md · 32 lines

What it actually says

Verification, in full

CLAUDE.md carries the commands an agent runs in-loop. Everything else lives here. Read only the file you need — each is self-contained.

  • reference/commands.md — the full command table: every verify:* sub-check, the infra-gated and credentialed test suites, test:mutate, model:multilevel, freeze:fold-stage0, all bench:*, the baerly deploy/doctor/export/inspect/admin surfaces, test:manual-e2e, and the published dist/API.md + dist/CHANGELOG.md references.
  • reference/test-gating.md — why a suite skipped: the MINIO=1 / credentials / Postgres / cloudflare-pool gates, the four randomized.test.ts storage variants, and the always-green pure-unit list.

Standing rules

Both apply for the rest of the session, not just the turn that loaded this.

  • Don't pipe verify:agent / test:agent / bundle-sizes through tail/head — they are already compact, and empty output means the gate passed.
  • Never call vitest via pnpm exec vitest or ./node_modules/.bin/vitest; both skip the pretest build hook and leave dist/ stale. test:agent does not rebuild dist/ either — run pnpm build first when a test consumes it.
Files

What ships with it

2 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.

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 · 32 lines · 87 tokens per session scan A bac7276b81c9

Subscribe to this mod's changes

verification is a skill published in the GitHub repository Gusto/baerly-storage (25 stars, last pushed today), licensed Apache-2.0. It adds 87 tokens to every session and 448 once invoked, about $0.0003 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.

DatabasesTestingappend-only-logbackend-as-a-servicecloudflare-workerscontent-addressable-storagedocument-database
Related

verification compared with skills from other repositories

verification next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
verificationGusto/baerly-storageSkill25todayApache-2.0A87Claude Code
butterbasebutterbase-ai/butterbaseSkill3.0kyesterdayApache-2.0A34Claude Code, Codex
build-appbutterbase-ai/butterbase-skillsSkill5356d agoMITA38Claude Code
schema-designbutterbase-ai/butterbase-skillsSkill5356d agoMITA31Claude Code
debug-rlsbutterbase-ai/butterbase-skillsSkill5356d agoMITA34Claude Code
journey-schemabutterbase-ai/butterbase-skillsSkill5356d agoMITA80Claude Code
journey-realtimebutterbase-ai/butterbase-skillsSkill5356d agoMITA62Claude Code