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/contentnpx skills add teejayen/arc --skill contentgit 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 | $0.00032 | $0.00630 |
| Opus 5 | $0.00016 | $0.00315 |
| Sonnet 5 | $0.00006 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
content 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Writing
Help write content for blog and social media platforms.
When to Use
- User asks to "write a post", "draft something", "write about X"
- Mentions blog, LinkedIn, or writing publicly
- Working on content for any platform
- Reviewing or editing existing drafts
Execution Steps
Step 1: Load context (if available)
Check for a content guide:
resources/content/CLAUDE.md
This may contain:
- Content strategy and pillars
- Voice and style guidance
- Platform-specific rules
- Examples of good posts
If no guide exists, ask the user about their content preferences.
Step 2: Review recent posts for voice consistency
Check recent published posts (if they exist):
ls -t resources/content/_posts/ | head -5
Read 2-3 recent posts to calibrate voice.
Step 3: Check planned content (if applicable)
If writing a scheduled post, check for calendars or planned content:
resources/content/content-calendar.md
resources/content/planned/
resources/content/series/
Step 4: Draft the content
Follow any loaded guidance. General good practices:
- Be authentic - write in the user's voice, not generic AI voice
- Ground in actual experience where possible
- Keep it concise (platform-appropriate length)
- Avoid corporate speak and cliches
- Use the user's preferred locale/spelling
Step 5: Self-check before presenting
Before showing the draft, verify:
- Does it sound like something the user would actually say?
- No corporate buzzwords or AI-sounding phrases
- Appropriate length for the platform
- Clear point or value to the reader
Step 6: Save draft if requested
If user asks to save:
Blog/social post:
resources/content/drafts/YYYY-MM-DD-slug.md
With frontmatter:
---
title: Post Title Here
status: draft
platform: [linkedin|blog|twitter|etc]
target_date: YYYY-MM-DD
theme: [philosophical|technical|leadership|personal|etc]
---
Workflow Reminder
- Long-form content -> blog
- Shorter intro -> social platforms that channel traffic to blog
- Ask about AI disclosure preferences if not defined
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 · 105 lines · 32 tokens per session scan A c2d76f9792ba
content is a skill published in the GitHub repository teejayen/arc (5 stars, last pushed 7mo ago), licensed MIT. It adds 32 tokens to every session and 630 once invoked, about $0.0002 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…