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 fanfan-de/anybox --skill onboardgit clone --depth 1 https://github.com/fanfan-de/anyboxWrote 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/fanfan-de/anybox/onboard)<a href="https://agentmods.dev/skills/fanfan-de/anybox/onboard"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/onboard/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/fanfan-de/anybox/onboard"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, 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 Excessive Agency · line 205 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 205 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 308 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00120 | $0.02447 |
| Opus 5 | $0.00060 | $0.01223 |
| Sonnet 5 | $0.00024 | $0.00489 |
| Haiku 4.5 | $0.00012 | $0.00245 |
Grade A, and why
onboarding 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 7d 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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CircleCI Onboarding
Guide the user through setting up CircleCI from scratch. Work through the
stages below in order. At each stage, use AskUserQuestion to collect
structured input rather than asking in prose — this keeps the flow crisp and
unambiguous. Run CLI commands to verify state before asking questions you can
answer yourself. Skip stages that are already complete.
Stage 0: Check prerequisites
First, verify the CLI version:
circleci version
Extract the version number from the output (e.g. circleci 0.1.2+... → 0.1.2).
If the major version is 0 (i.e. below 1.0.0), stop and tell the user:
"This onboarding flow requires CircleCI CLI version 1.0.0 or later. Your installed version is
<version>. Please upgrade with:brew tap circleci-public/homebrew-circleci brew remove circleci brew install --cask circleci@next ```"
Do not proceed past this stage if the version check fails.
Then run circleci auth me before asking anything. If it returns a user, skip
Stage 1 and note the username.
Stage 1: Account
If not authenticated, ask:
AskUserQuestion(
"Are you new to CircleCI or do you already have an account?",
header: "Account",
options: [
{ label: "New — create an account", description: "Open signup in browser via circleci auth signup" },
{ label: "Existing — log in", description: "Open login in browser via circleci auth login" }
]
)
Then run the appropriate command and verify with circleci auth me.
Stage 2: Org
Ask:
AskUserQuestion(
"Which CircleCI org do you want to use?",
header: "Organization",
options: [
{ label: "Use an existing org", description: "I'll provide the org slug" },
{ label: "Create a new org", description: "I'll walk you to app.circleci.com/organization-setup" }
]
)
- Existing: Ask for the slug via a follow-up text input (e.g.
gh/myorgorcircleci/<uuid>). Found at Organization Settings → Organization slug. - New: Direct to
https://app.circleci.com/organization-setup, wait for confirmation, then ask for the resulting slug.
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.
- 7d ago First seen · 314 lines · 120 tokens per session scan A bb139766139e
onboarding is a skill published in the GitHub repository fanfan-de/anybox (57 stars, last pushed 28d ago), licensed MIT. It adds 120 tokens to every session and 2,447 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
import-prom-rule
Bulk import of a Prometheus alert rule YAML file (create a whole set of rules at once). Dedicated to handling a remote URL or local YAML text, automatically parsing the three formats groups / a plain rules array / a single rule. ⚠️ Do not use this skill for single-rule creation — when the user describes a single alert…
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
configure-env-variables
Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…
atmos-profiles
Atmos profiles: profile directories, --profile and ATMOSPROFILE activation, profile merge behavior, environment switching, and routing profile-specific auth/toolchain/config overrides.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
managing-github-actions-secrets
Creates and updates GitHub Actions secrets for PostHog workflows. Use when adding a new CI secret, rotating an existing secret, wiring a workflow to an API token, package registry credential, deploy key, or any value referenced via ${{ secrets. }} in .github/workflows/.