init

init is a command for Claude Code from jamditis/claude-skills-journalism. It costs 13 tokens per session (1,337 once invoked), scanned A, original, MIT.

A command that sets up an .autocontext directory in a project for storing shared project knowledge and lessons. It can also use an existing CLAUDE.md file as a starting point.

In plain words
What is it for?
Use it when starting project knowledge storage, choosing whether to import lessons from CLAUDE.md, or deciding whether other developers should share the setup.
Why use it?
It gives a project a consistent place to keep context for future coding-agent sessions, reducing the need to explain the same project rules repeatedly. Existing lessons are preserved when configuration is reset.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the autocontext plugin — 5 commands, 1 agent shipped together

Good fit Use it when starting project knowledge storage, choosing whether to import lessons…

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add jamditis/claude-skills-journalism
Claude Code
/plugin install autocontext

Made for: Claude Code.

Or install autocontext, the plugin that ships this one along with the rest of its 5 commands, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for init

README.md
[![agentmods](https://agentmods.dev/badge/commands/jamditis/claude-skills-journalism/init.svg)](https://agentmods.dev/commands/jamditis/claude-skills-journalism/init)
Your own site
<a href="https://agentmods.dev/commands/jamditis/claude-skills-journalism/init"><img src="https://agentmods.dev/badge/commands/jamditis/claude-skills-journalism/init.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,337 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00013 $0.01337
Opus 5 $0.00006 $0.00668
Sonnet 5 $0.00003 $0.00267
Haiku 4.5 $0.00001 $0.00134

Measured 7d ago against content hash 2adbbaaa7954, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 7d 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.

autocontext/commands/init.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Initialize the autocontext knowledge directory in the current project. Use AskUserQuestion for setup decisions.

Pre-initialization check

First, the script checks if .autocontext/ already exists in the project root. If it does, you'll be informed and asked:

Question: This project already has autocontext initialized. Reinitialize?

Options:

  • Yes, set up fresh configuration (existing lessons are NOT deleted)
  • No, exit and use current setup

If you choose to reinitialize, existing lessons in .autocontext/lessons.json will be preserved but all config files will be reset.

Setup questions

Step 1: Seed from CLAUDE.md (if applicable)

If a CLAUDE.md file exists in the project root:

Question: This project has a CLAUDE.md. Seed initial lessons from it?

Options:

  • Yes, extract and let me review each one, parses CLAUDE.md and shows each extracted lesson for approval
  • Yes, extract automatically, extracts all lessons without review
  • No, start fresh, begins with empty lessons

This helps bootstrap project knowledge from existing documentation.

Step 2: Cross-developer sharing

Question: Will other developers use Claude Code on this repo?

Options:

  • Yes, set up cross-developer sharing, enables the union merge driver for collaborative lesson management
  • No, just me, single-developer setup, simpler merge strategy

Cross-developer sharing allows multiple Claude instances to work on the same lessons.json without conflicts.

Step 3: Performance baselines

Question: Track test/build performance baselines?

Options:

  • Yes, initialize baseline tracking for test and build performance
  • No, skip baseline tracking

Performance baselines help detect regressions in test suite and build times over time.

Directory structure creation

The script will create the following structure in .autocontext/:

.autocontext/
├── config.json              # Project configuration (shared)
├── config.local.json        # Local developer identity
├── lessons.json             # Accumulated lessons (git-tracked)
├── playbook.md              # Curated lesson playbook (auto-generated)
├── .gitignore               # Ignore cache and local files
├── .gitattributes           # (if sharing enabled) Configure merge driver
├── cache/                   # Temporary files (not git-tracked)
│   ├── pending-lessons.json # (if ask_before_persist) Awaiting approval
│   └── curated-pending.json # From /autocontext:review sessions
└── archive/                 # Tombstoned lessons (git-tracked)
    └── superseded.json      # Deleted lessons for reference

Read the full file on GitHub · 143 lines

Changes

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.

  1. 7d ago First seen · 143 lines · 13 tokens per session scan A 2adbbaaa7954

Subscribe to this mod's changes

init is a command published in the GitHub repository jamditis/claude-skills-journalism (386 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 1,337 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 2026-08-30.