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 agentmods add skills/howells/arc/launchnpx skills add howells/arc --skill launchgit clone --depth 1 https://github.com/howells/arcWhat 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 | $0.00064 | $0.03131 |
| Opus 5 | $0.00032 | $0.01566 |
| Sonnet 5 | $0.00013 | $0.00626 |
| Haiku 4.5 | $0.00006 | $0.00313 |
Grade A, and why
launch 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 2d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<tool_restrictions>
Ask one question at a time. In Claude Code use AskUserQuestion; elsewhere ask a single concise plain-text question. Keep any lead-in to 2-3 sentences. Don't narrate missing tools or fallbacks.
</tool_restrictions>
<arc_runtime>
Requires the full Arc bundle. Arc-owned paths (agents/, references/, disciplines/, templates/, scripts/, rules/, skills/) resolve from the plugin root — the directory containing agents/ and skills/. Everything else is the user's repository.
</arc_runtime>
<required_reading> Read this reference before building the final status:
references/launch-scorecard.md
</required_reading>
Launch Workflow
Prepare a project to go live and be shareable. This is a checklist workflow, not a deep remediation workflow.
- Do not start a dev server, preview server, tunnel, deployment, or browser session just to answer
/arc:launch. - Do not run exploratory UI QA or say the app "looks good" from a shallow homepage check.
- Do not create, update, or redeploy hosting resources unless the user explicitly asks.
- Do not change DNS, environment variables, provider dashboard settings, auth callbacks, payment webhooks, robots policy, or metadata unless the user explicitly asks.
- If a local or public URL is already provided, you may record it as evidence. If none is known, mark the public URL as
MissingorNeeds user. - If rendered verification would be useful, list it as a next action instead of doing it automatically.
Launch should answer:
- Can someone visit it at a public URL?
- Can someone share it and get a decent preview?
- Are obvious placeholders, local-only settings, access gates, and missing assets gone?
- Are detected services configured for the public URL?
- Are accidental launch blockers such as
noindex, disallow rules, maintenance mode, or preview passwords absent or intentional? - Have deeper checks been run or intentionally deferred?
If the work turns into deep code health, security remediation, or safety-net test backfill, route outside launch instead:
- Codebase health, risk, and security remediation ->
/arc:audit - Untested behavior that needs a safety net ->
/arc:testing
What ships with it
1 file 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.
- 2d ago First seen · 278 lines · 64 tokens per session scan A 97468a345515
launch is a skill published in the GitHub repository howells/arc (25 stars, last pushed 18d ago), licensed MIT. It adds 64 tokens to every session and 3,131 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
n8n-agents
Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain. AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output…
n8n-error-handling
Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error…
n8n-subworkflows
Build reusable, composable n8n sub-workflows. Use when extracting shared logic, building anything multi-step or reused across workflows, or any workflow over 10 nodes — and whenever the user mentions sub-workflows, Execute Workflow, reuse, shared/common logic, modular workflows, "Define Below" inputs…
n8n-validation-expert
Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities.…
n8n-binary-and-data
Handle files and binary data in n8n correctly. Use when working with files, images, PDFs, attachments, uploads or downloads, base64, vision/multimodal input, or when an AI agent needs a file as tool input or output — and whenever the user mentions $binary, binaryPropertyName, "read the PDF", "attach the file", "send…
n8n-code-tool
Write JavaScript or Python for the n8n Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode) — the AI-agent-callable tool, NOT the workflow Code node. Use when building a Code Tool attached to an AI Agent, writing code that an LLM will invoke, parsing the query input, returning a string result, defining an input schema…