Open-Inspect is a hosted system that lets coding agents work on software tasks in background development environments. Teams use it to connect agents with repositories, communication tools, scheduled events, and parallel sandboxes. The catalogue contains add-ons associated with this system.
Borrowing it
Nothing to install: this file belongs to ColeMurray/background-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ColeMurray/background-agents/main/.claude/skills/onboarding/SKILL.mdgit clone --depth 1 https://github.com/ColeMurray/background-agentsWrote 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/colemurray/background-agents/onboarding)<a href="https://agentmods.dev/skills/colemurray/background-agents/onboarding"><img src="https://agentmods.dev/badge/skills/colemurray/background-agents/onboarding/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/colemurray/background-agents/onboarding"><img src="https://agentmods.dev/badge/skills/colemurray/background-agents/onboarding.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 Data Exfiltration · line 190 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium MCP Rug Pull · line 336 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 337 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00047 | $0.04101 |
| Opus 5.5 | $0.00019 | $0.01640 |
| Sonnet 5.5 | $0.00009 | $0.00820 |
| Haiku 4.5 | $0.00005 | $0.00410 |
Grade C, and why
onboarding scanned grade C with 2 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 1mo 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
Hand off to user for each service. Use AskUserQuestion to collect credentials. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl https://open-inspect-control-plane-{deployment_name}.{subdomain}.workers.dev/health How it starts
The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open-Inspect Deployment Guide
You are guiding the user through deploying their own instance of Open-Inspect. This is a multi-phase process requiring user interaction for credential collection and external service configuration.
Before Starting
Use TodoWrite to create a checklist tracking these phases:
- Initial setup questions
- Repository setup
- Credential collection (Cloudflare, Vercel if selected, Modal, Anthropic)
- GitHub App creation (+ Google OAuth if enabled)
- Slack App creation (if enabled)
- Security secrets generation
- Terraform configuration
- Terraform deployment (two phases)
- Post-deployment Slack setup (if enabled)
- Post-deployment GitHub Bot setup (if enabled)
- Web app deployment
- Workspace Owner bootstrap
- Verification
- CI/CD setup (optional)
Phase 1: Initial Questions
First, generate a random suffix suggestion for the user:
echo "Suggested deployment name: $(openssl rand -hex 3)"
Use AskUserQuestion to gather:
- Directory location - Where to create the project (default: current directory or ~/workplace/open-inspect-{suffix})
- GitHub account - Which account/org hosts the private repo
- Deployment name - A unique identifier for deployment URLs (e.g., their GitHub username, company name, or the random suffix generated above); Vercel project URLs must be globally unique.
- Web platform - Vercel (default) or Cloudflare Workers. If Cloudflare, ask whether to use a
custom domain; if so, collect the hostname and Cloudflare zone ID. Derive one canonical web app
URL from this choice and the deployment name using Step 3 of
docs/GETTING_STARTED.md; use it for both OAuth callbacks and the GitHub App homepage. - Slack integration - Yes or No
- GitHub bot integration - Yes or No (automated PR reviews and comment-triggered actions)
- Sign-in providers - GitHub, Google, or both. At least one is required.
- Admission mode - Restricted (collect the allowed GitHub usernames, exact verified emails,
email domains, and/or GitHub orgs) or explicitly open to any authenticated user (no allowlists).
Validate the chosen providers and admission mode against the compatibility table and allowlist
rules in Step 5 of
docs/GETTING_STARTED.mdbefore proceeding. - Prerequisites confirmation - Confirm they have Cloudflare, Modal, Anthropic, and GitHub accounts, plus Vercel only if selected above.
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.
- 1mo ago Changed · +4 lines bd636db02bcc
- 1mo ago Changed · +33 lines de6c0d2032ac
- 2mo ago First seen · 374 lines · 47 tokens per session scan C 11d6ef398a81
onboarding is a skill published in the GitHub repository ColeMurray/background-agents (3,433 stars, last pushed 6d ago), licensed MIT. It adds 47 tokens to every session and 4,101 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (harvests environment variables, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
onboarding compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| onboardingColeMurray/background-agents | Skill | 3.4k | 6d ago | MIT | C | 47 | Claude Code |
| deploy-open-harnessvercel-labs/open-agents | Skill | 5.9k | 2mo ago | MIT | A | 60 | Claude Code, Codex |
| datasources-infractxpipe-ai/ctxpipe | Skill | 27 | today | MIT | A | 64 | Claude Code, Codex |
| gke-compute-classesgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 83 | Claude Code, Codex |
| gke-reliabilitygoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 85 | Claude Code, Codex |
| gke-workload-securitygoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 171 | Claude Code, Codex |
| nemo-automodel-launcher-configNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 30 | Claude Code |