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/teejayen/arc/setupnpx skills add teejayen/arc --skill setupgit clone --depth 1 https://github.com/teejayen/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 | $0.00021 | $0.02243 |
| Opus 5 | $0.00010 | $0.01122 |
| Sonnet 5 | $0.00004 | $0.00449 |
| Haiku 4.5 | $0.00002 | $0.00224 |
Grade A, and why
setup 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 — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup
Customise Arc for your personal use. This wizard gathers information about you, helps you articulate your guiding principles, and generates personalised configuration files.
When to Use
- First time using Arc
- Want to update your context or preferences
- Adding new projects or life areas
- Refining your guiding principles
- Changing communication preferences
Execution Steps
Step 1: Welcome
Introduce Arc and explain what this setup will do:
Welcome to Arc - your personal thinking partner.
I'll help you set up Arc through a conversation. We'll cover:
- Who you are and what you're working on
- Your guiding principles (what matters, how you want to spend your time)
- Privacy settings for sensitive terms
- Any context you want me to understand
The more context you give me, the better I can think alongside you.
Let's get started.
Step 2: Gather Context via Inbox
Encourage the user to dump context into the inbox:
Before we dive into questions, here's an idea:
If you have existing documents that capture who you are - journal entries,
notes, plans, reflections, even old todo lists - drop them into the `inbox/`
folder. I'll review them and use that context to understand you better.
This could include:
- Notes from previous AI conversations
- Annual reviews or reflections
- Project plans or ideas
- Anything that captures how you think
Want to add anything to inbox/ first, or shall we proceed with questions?
If they add files to inbox:
ls -la inbox/
Read each file and extract:
- Recurring themes
- Projects mentioned
- Values or principles implied
- Communication style
- Life areas that matter to them
Use this context to inform the questions and to pre-populate configuration.
Step 3: Personal Context
Ask about the user. Be conversational, not interrogative. Adapt based on what you learned from inbox context.
Questions to explore (adapt based on their responses):
-
"What should I call you?"
-
"What's your work context? This helps me understand your day-to-day. (Job title, company/industry - as much or little as you want to share)"
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 · 363 lines · 21 tokens per session scan A f2d5a66306cc
setup is a skill published in the GitHub repository teejayen/arc (5 stars, last pushed 7mo ago), licensed MIT. It adds 21 tokens to every session and 2,243 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…