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/testingnpx skills add howells/arc --skill testinggit 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 | $0.00070 | $0.03124 |
| Opus 5 | $0.00035 | $0.01562 |
| Sonnet 5 | $0.00014 | $0.00625 |
| Haiku 4.5 | $0.00007 | $0.00312 |
Grade A, and why
testing 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 — 317 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.
EnterPlanMode and ExitPlanMode are banned. This skill is Arc's own structured testing process.
</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>
Characterization Testing Workflow
Backfill focused tests around existing code before a risky change. The goal is not "more tests" in the abstract; it is a trustworthy safety net around behavior that must survive a refactor, migration, or bug fix.
Use this skill when:
- Existing code has little or no test coverage.
- A refactor needs a behavior-preserving safety net first.
- A god file, duplicated implementation, or tangled module needs characterization before decomposition.
- A performance optimization needs current behavior pinned before changing data structures, batching, memoization, caching, or ordering.
- A bug fix touches unclear behavior and you need to capture the current contract before changing it.
- Coverage reports show gaps around important public behavior.
- Auth, API, state, or browser flows need targeted tests before launch or audit remediation.
Do not use this skill as the normal new-feature workflow. For new work, use /arc:implement or a dedicated TDD skill so RED/GREEN/REFACTOR remains the governing loop.
<required_reading> Read before testing:
references/testing-patterns.md— Test philosophy, vitest/playwright patternsreferences/testing-anti-patterns.md— What weak or misleading tests look likerules/testing.md— Arc testing conventions, when the project has no rules of its own (see<rules_context>)disciplines/change-impact-testing.md— loaded for its blast-radius framing only. It is a post-change discipline, so its revert-the-change sensitivity proof does not apply here; on a backfill run there is no change to revert, and the perturbation method in Step 4 is the sensitivity proof.references/llm-api-testing.md— If testing LLM integrationsreferences/maintainability-review.md— If tests are being added before decomposing a god file or tangled modulereferences/complexity-optimization.md— If tests are being added before optimizing algorithmic complexity, rendering churn, or N+1 behavior </required_reading>
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 · 317 lines · 70 tokens per session scan A 66051bc42336
testing is a skill published in the GitHub repository howells/arc (25 stars, last pushed 17d ago), licensed MIT. It adds 70 tokens to every session and 3,124 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-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…