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 backblaze-labs/claude-skill-b2-cloud-storage --skill b2-cloud-storagegit clone --depth 1 https://github.com/backblaze-labs/claude-skill-b2-cloud-storageWrote 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/backblaze-labs/claude-skill-b2-cloud-storage/b2-cloud-storage)<a href="https://agentmods.dev/skills/backblaze-labs/claude-skill-b2-cloud-storage/b2-cloud-storage"><img src="https://agentmods.dev/badge/skills/backblaze-labs/claude-skill-b2-cloud-storage/b2-cloud-storage/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/backblaze-labs/claude-skill-b2-cloud-storage/b2-cloud-storage"><img src="https://agentmods.dev/badge/skills/backblaze-labs/claude-skill-b2-cloud-storage/b2-cloud-storage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 9 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00057 | $0.01180 |
| Opus 5 | $0.00028 | $0.00590 |
| Sonnet 5 | $0.00011 | $0.00236 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade A, and why
b2-cloud-storage 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
B2 Cloud Storage Management
Manage Backblaze B2 cloud storage: list files, audit usage, estimate cost, clean up stale data, and review security posture.
Security Rules (MANDATORY)
- Never run
b2 account get,b2 account clear, or anyb2 key *subcommand — these expose or mutate credentials. - Never read
~/.b2_account_infoor any file matching*b2_account_info*— this is the B2 credential database (SQLite). - Always run
b2 rm --dry-runbefore any real deletion; show the user what would be deleted and require an explicit "yes" before executing. - Never change a bucket to
allPublicwithout first warning the user about the security implications and getting explicit confirmation. - Default to read-only — only perform writes or deletes when the user explicitly requests them.
- Never store or write API keys, application keys, or account IDs to any file.
- If the user pastes key values into the chat instead of the terminal, warn them immediately and recommend rotating the key. Never echo, store, or reference key values that appear in conversation.
First-Use Flow
- Check the B2 CLI is installed:
b2 version. If missing, ask the user to install the CLI outside the agent, then rerunb2 version- seereferences/setup.mdfor detail. - Verify the CLI is authorized:
b2 ls. If it fails with an auth error, walk the user throughreferences/setup.md. - Check for a per-project config at
.claude/b2-config.jsonin the project root. If missing, ask the user for bucket + prefix and create one.
Interactive auth note
b2 account authorize (no args) reads keys from an interactive prompt, which agents cannot drive. The user has two options:
- Run it themselves in the terminal — in Claude Code they can type
!b2 account authorizeto execute directly in the session. - Pass the keyID and applicationKey as positional args:
b2 account authorize <keyID> <appKey>(keys will appear in shell history — less safe). - Or set
B2_APPLICATION_KEY_IDandB2_APPLICATION_KEYenv vars before running B2 commands (recommended for scripts and CI).
What ships with it
7 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.
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.
- 9d ago First seen · 111 lines · 57 tokens per session scan A 2c2de1b93843
b2-cloud-storage is a skill published in the GitHub repository backblaze-labs/claude-skill-b2-cloud-storage (40 stars, last pushed 21d ago), licensed MIT. It adds 57 tokens to every session and 1,180 once invoked, about $0.0003 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
disaster-recovery-plan
Write a disaster recovery and business continuity plan defining RTO/RPO targets, backup and failover procedures, DR tiers, and a recovery drill cadence for surviving major infrastructure loss, data corruption, ransomware, or regional outages. Use before launch of any system holding critical or financial data, or to…
slo-error-budget-document
Define Service Level Indicators (SLIs), Service Level Objectives (SLOs), and error budgets for a service, including multi-window multi-burn-rate alerting and an error budget policy. Use when establishing reliability targets, negotiating an external SLA, or deciding how much risk a team can spend on shipping velocity…
companion-clis
Companion CLIs for Runpod workflows — HuggingFace, GitHub, Docker, and AWS.
cloud-deployment-routing-workflow
Choose a cloud deployment path before implementation. Route AWS work to the official AWS Agent Toolkit and Azure work to Microsoft's Azure Skills plugin while keeping credentials, regions, and mutation boundaries explicit.
macos-distribution-workflow
Inspect, prepare, validate, and troubleshoot exported macOS distribution artifacts. Use when checking signing identities, entitlements, hardened runtime, nested code, Gatekeeper, notarization readiness/results, stapling, or distribution-only launch failures.
prepare-isolated-analysis-lab
Prepare a verified disposable Linux or macOS analysis lab from an approved isolation decision. Use before active research to control host integration, networking, baseline, monitoring, evidence export, reset, and teardown.