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/reviewnpx skills add howells/arc --skill reviewgit 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 | $0.00068 | $0.03347 |
| Opus 5 | $0.00034 | $0.01673 |
| Sonnet 5 | $0.00014 | $0.00669 |
| Haiku 4.5 | $0.00007 | $0.00335 |
Grade A, and why
review 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 — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<tool_restrictions>
EnterPlanMode and ExitPlanMode are banned. This skill is Arc's own structured 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>
<required_reading> Read these reference files NOW:
- references/review-patterns.md
- references/question-loops.md — the one-question-at-a-time rules Phase 4 runs on
- disciplines/dispatching-parallel-agents.md
- disciplines/receiving-code-review.md </required_reading>
<rules_context> Check for project coding rules:
Use Glob tool: .ruler/*.md
Determine rules source:
- If
.ruler/exists: Read rules from.ruler/ - If
.ruler/doesn't exist: Read rules fromrules/
Pass relevant core rules to each reviewer:
| Reviewer | Rules to Pass |
|---|---|
| daniel-product-engineer | react.md, typescript.md, code-style.md |
| lee-nextjs-engineer | nextjs.md, api.md |
| senior-engineer | code-style.md, typescript.md, react.md; cloudflare-workers.md if wrangler.toml exists |
| architecture-engineer | stack.md, turborepo.md |
| mastra-agent-engineer | api.md, integrations.md, typescript.md |
| security-engineer | security.md, api.md, env.md |
| data-engineer | database.md, testing.md, api.md |
| performance-engineer | react-performance.md, api.md |
| test-quality-engineer | testing.md |
| accessibility-engineer | (interface rules only — already in agent prompt) |
The table names Arc's own rules/ files. When .ruler/ exists, glob it first and match by topic rather than by these filenames.
</rules_context>
<scope_discipline>
Scope Discipline
Reviewers must respect the plan's scope. This is non-negotiable:
- Do not silently argue for less work. If you think the plan is overbuilt, raise it once in a "Scope Check" early in the review. After the user responds, commit to their decision.
- Do not sneak in additional scope. Don't suggest features, enhancements, or "while you're at it" additions beyond what the plan covers.
- Your job is to make this plan succeed, not to lobby for a different plan. Once scope is agreed, optimize within it — find bugs, catch edge cases, improve the architecture — but don't re-litigate what gets built.
- Include this principle in every reviewer prompt: "Respect the plan's scope. Flag scope concerns once, then commit to making the plan succeed." </scope_discipline>
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 · 356 lines · 68 tokens per session scan A b1e620cc53d1
review is a skill published in the GitHub repository howells/arc (25 stars, last pushed 18d ago), licensed MIT. It adds 68 tokens to every session and 3,347 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…