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/pattern-scannpx skills add teejayen/arc --skill pattern-scangit 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 | $0.00037 | $0.01107 |
| Opus 5 | $0.00018 | $0.00553 |
| Sonnet 5 | $0.00007 | $0.00221 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
pattern-scan 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pattern Scan
Analyse journal.jsonl to surface patterns across time - what's recurring, what's neglected, energy trends, and avoidance patterns.
When to Use
- Wanting perspective on where attention has been going
- Feeling scattered - what's actually getting focus?
- Noticing something keeps coming up
- Weekly/monthly reflection
- Sensing avoidance but not sure of what
Data Source
Primary: state/journal.jsonl
Each entry:
{
"t": "2025-12-28T09:10",
"topics": ["planning", "strategy", "project-x"],
"energy": "high|medium|low",
"areas": ["projects", "learning"],
"summary": "One-line session summary"
}
Secondary: sessions/ folder for deeper context (files named YYYY-MM-DD-HHMM-topic.md).
Execution Steps
Step 1: Load Data
cat state/journal.jsonl
Parse all entries. Note the date range covered.
Step 2: Topic Frequency
Count occurrences of each topic across all entries.
Present as:
## Topic Frequency (last N sessions)
| Topic | Count | % of Sessions |
|-------|-------|---------------|
| project-x | 5 | 100% |
| content | 3 | 60% |
| planning | 2 | 40% |
| ...
Flag:
- Dominant topics: Appearing in >50% of sessions
- One-offs: Appeared once, might indicate unfinished thread
- Emerging: New in recent sessions
Step 3: Area Coverage
Which life areas are getting attention?
## Area Coverage
| Area | Sessions | Last Touched |
|------|----------|--------------|
| projects | 5 | today |
| learning | 2 | 2025-12-27 |
| career | 0 | never |
| family | 0 | never |
| health | 0 | never |
Flag:
- Neglected: Areas with 0 sessions or not touched in 2+ weeks
- Dominant: Areas consuming >40% of sessions
- Balanced: Areas with steady, moderate attention
Step 4: Energy Patterns
Track energy levels over time:
## Energy Trend
| Date | Energy | Topics |
|------|--------|--------|
| 2025-12-28 | high | planning, strategy |
| 2025-12-27 | high | content, writing |
| 2025-12-26 | medium | admin, cleanup |
| ...
**Pattern**: Mostly high energy sessions - sustainable, or avoiding low-energy work?
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 · 183 lines · 37 tokens per session scan A 5b8460921dd0
pattern-scan is a skill published in the GitHub repository teejayen/arc (5 stars, last pushed 7mo ago), licensed MIT. It adds 37 tokens to every session and 1,107 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…