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/using-arcnpx skills add howells/arc --skill using-arcgit 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 | $0.00022 | $0.01317 |
| Opus 5 | $0.00011 | $0.00659 |
| Sonnet 5 | $0.00004 | $0.00263 |
| Haiku 4.5 | $0.00002 | $0.00132 |
Grade A, and why
using-arc 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<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.
Prompt-only installers (skills.sh and similar) copy SKILL.md files without Arc's bundled material. If a workflow needs Arc-owned files and only prompt-only skills are present, stop early and tell the user to upgrade to the full Claude, Codex, or Cursor plugin install.
</arc_runtime>
Using Arc
Arc's canonical product definition, domain language, and operating boundary live in
CONTEXT.md at the Arc repository root. This skill applies that context at session
startup.
Arc has a broad workflow surface. Use this skill as the small control plane that decides how to route work without loading every workflow into context at once.
Arc is self-contained and lifecycle-focused. Its job is to move software work from idea to shipped code through Arc-owned workflows, not to act as a general registry for external personal skills. When a specialist practice is useful, absorb it into the relevant Arc workflow in Arc's own language.
Instruction Priority
When instructions conflict, use this order:
- User instructions in the conversation
- Project instructions (
AGENTS.md,CLAUDE.md, repo docs) - Arc skills
- Default system behavior
The user stays in control. Arc provides process, not authority over explicit user intent.
The Rule
Before substantial work, decide whether an Arc skill clearly applies.
- If the user names an Arc skill, use it.
- If the task clearly matches an Arc workflow, use that skill before acting.
- If the task is small, direct, or outside Arc's workflows, respond normally.
Arc should improve routing, not create ceremony for every trivial request.
Do not route users to external skill collections as part of Arc's normal operation. External skills can inspire Arc workflow design, but Arc workflows must remain usable on their own.
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 · 128 lines · 22 tokens per session scan A b2a9702cc573
using-arc is a skill published in the GitHub repository howells/arc (25 stars, last pushed 18d ago), licensed MIT. It adds 22 tokens to every session and 1,317 once invoked, about $0.0001 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-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…
n8n-multi-instance
Use when an n8n-mcp account targets more than one n8n instance — i.e. the n8ninstances tool is available, the user mentions multiple n8n instances or environments (prod vs staging, several teams or clients), a workflow / datatable / credential / execution call returns an unexpected NOTFOUND or reads data you don't…