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/alaarab/phren/initnpx skills add alaarab/phren --skill initgit clone --depth 1 https://github.com/alaarab/phrenWhat 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 | $0.00024 | $0.01376 |
| Opus 5 | $0.00012 | $0.00688 |
| Sonnet 5 | $0.00005 | $0.00275 |
| Haiku 4.5 | $0.00002 | $0.00138 |
Grade A, and why
init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
92% identical to phren-init — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
phren-init - Scaffold a new project
Set up a new project in phren with summary, CLAUDE.md, task, and skill templates.
Tell phren about a new project, or bootstrap phren himself if you're starting fresh.
Usage
phren-init my-new-project # scaffold a specific project
phren-init # list existing projects, suggest unconfigured ones
First: find or create the phren directory
PHREN_DIR="${PHREN_DIR:-$HOME/.phren}"
ls "$PHREN_DIR" 2>/dev/null
If the phren directory doesn't exist, offer to create it:
"No phren repo found. Want me to create one at ~/.phren? This will set up the base directory structure (global/, profiles/, machines.yaml)."
If the user says yes, create the base structure:
mkdir -p "$PHREN_DIR"/{global/skills,profiles}
# Create a starter machines.yaml
# Create a starter profile
Then continue with the project scaffolding below.
With a project name
1. Check it doesn't already exist
ls "$PHREN_DIR/<project-name>/" 2>/dev/null
If it exists, tell the user and ask if they want to reset it or just update specific files.
2. Create the project directory
mkdir -p "$PHREN_DIR/<project-name>/skills"
3. Create summary.md
This is the project's identity card. Five lines, no more.
# <project-name>
What: <one sentence about what this project does>
Stack: <languages, frameworks, key deps>
Status: <active / maintenance / new / archived>
Run: <the main command to start it, e.g. "npm run dev">
Watch out: <the one thing that trips people up>
Ask the user for these if you can't figure them out from the project directory. If the project directory exists on disk (e.g. ~/<project-name>/), read its package.json, pyproject.toml, README, or similar to pre-fill.
4. Create CLAUDE.md
# <project-name>
<One paragraph: what this project is and what it does.>
## Commands
Architecture
Conventions
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 · 217 lines · 24 tokens per session scan A beea5673b78e
init is a skill published in the GitHub repository alaarab/phren (4 stars, last pushed 7d ago), licensed MIT. It adds 24 tokens to every session and 1,376 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to phren-init, differing in 8 lines, and is treated as a copy.
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…