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/releasenpx skills add howells/arc --skill releasegit 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 | $0.00075 | $0.04082 |
| Opus 5 | $0.00037 | $0.02041 |
| Sonnet 5 | $0.00015 | $0.00816 |
| Haiku 4.5 | $0.00007 | $0.00408 |
Grade A, and why
release 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 yesterday.
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 — 259 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.
</arc_runtime>
<platform_context> Adapt the workflow to the current harness instead of assuming Claude-specific tool names.
- Use platform-native structured questions when available; otherwise ask one concise plain-text question at a time.
- Use the repo's detected package manager (
pnpm,npm,yarn,bun) consistently for every command below. Commands are written with a<pm>placeholder — substitute the detected manager. - Detect
<pm>in this order: thepackageManagerfield inpackage.json, then a lockfile (pnpm-lock.yaml→ pnpm,package-lock.json→ npm,yarn.lock→ yarn,bun.lockb→ bun), then default tonpm. - The changesets workspace-root install flag
-wapplies only under pnpm; drop it for npm, yarn, and bun. - Publishing itself uses
npm publishregardless of the install-time package manager. Changeset-driven publishes run through the detected manager (<pm> changeset publish).
</platform_context>
Release Workflow
Cut a versioned release of one or more npm packages. /arc:commit publishes a package whose version is already committed and not yet on the registry. /arc:release owns bumping versions, changelogs, and coordinated multi-package releases.
The canonical order across both skills is commit → push → publish → tag. /arc:commit states the governing invariant — never publish before pushing the commit containing the package version — and this skill follows it.
Usage:
/arc:release- Detect, propose bumps, author, verify, commit and push, then gate publish./arc:release dry-run- Run everything up to and includingnpm packverification, but never commit, publish, tag, or push.
$ARGUMENTS will be empty or "dry-run". Treat "dry-run" as a hard stop before any publish.
Resolve the run mode first: the dry-run argument, or any unattended gate fallback, sets mode = dry-run for the remainder of the run. In dry-run mode Steps 3 and 5 are skipped entirely, and Step 6 reports instead of publishing. Once set, the mode never clears — carry it to the report.
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.
- yesterday First seen · 259 lines · 75 tokens per session scan A 2ea04502cce7
release is a skill published in the GitHub repository howells/arc (25 stars, last pushed 17d ago), licensed MIT. It adds 75 tokens to every session and 4,082 once invoked, about $0.0004 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…