agentmods.dev

init

A command that creates the starting files and folders for an LLM wiki, a knowledge base compiled with a language model. It creates places for original sources, categorized wiki pages, an index, a log, and the rules that pages should follow.

In plain words
What is it for?
Use it to start a new research wiki in an empty directory. Afterward, you can place source files in raw/ and run the wiki's ingestion command to compile them.
Why use it?
It removes the repetitive setup needed before adding research to a wiki. It also checks whether the current directory is safe to initialize before creating the structure.

Command

4 4mo ago A scan 45 tokens original MIT
View the source file doneyli/claude-code-plugins
Install

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.

agentmods
npx agentmods add commands/doneyli/claude-code-plugins/init
Clone the repo
git clone --depth 1 https://github.com/doneyli/claude-code-plugins
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 457 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00045 $0.00457
Opus 5 $0.00023 $0.00229
Sonnet 5 $0.00009 $0.00091
Haiku 4.5 $0.00005 $0.00046

Measured yesterday against content hash 951e41b6ce6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

llm-wiki/commands/init.md · 58 lines

What it actually says

Scaffold a Karpathy-style LLM wiki in the current working directory.

Steps:

  1. Check that the current directory is either empty or contains only a .git/. If it has existing content beyond that, warn the user and ask before proceeding.

  2. Create the directory structure:

    • raw/
    • wiki/
    • wiki/entities/
    • wiki/concepts/
    • wiki/themes/
    • wiki/comparisons/
    • wiki/synthesis/

  3. Write wiki/index.md with empty category sections:

    # Wiki Index

## Entities
_No pages yet._

## Concepts
_No pages yet._

## Themes
_No pages yet._

## Comparisons
_No pages yet._

## Synthesis
_No pages yet._

  4. Write wiki/log.md:

    # Wiki Log

Append-only. Format: `## [YYYY-MM-DD] <op> | <title>` where op ∈ {ingest, query, lint}.

  5. Copy the schema template from ${CLAUDE_PLUGIN_ROOT}/templates/CLAUDE.md to the current directory. If an argument was given ($1), substitute the {{DOMAIN_TITLE}} placeholder with it. Otherwise use "Research".

  6. Create a .gitignore that excludes raw/_originals/.

  7. Print a summary:

    • "Wiki initialized at $(pwd)"
    • "Next: drop a markdown file into raw/ then run /llm-wiki:ingest "
    • "Or: /llm-wiki:ingest --all to compile every file in raw/"

If CLAUDE.md already exists in the current directory, do NOT overwrite it. Report "Wiki already initialized here" and exit.

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. yesterday First seen · 58 lines · 45 tokens per session scan A 951e41b6ce6b

Subscribe to this mod's changes

init is a command published in the GitHub repository doneyli/claude-code-plugins (4 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 457 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.

Data and AIMemory and contextResearch
Related

Other commands, from other repositories

checklist

Generate a custom checklist for the current feature based on user requirements.

github/spec-kit · 13 tokens

clarify

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

github/spec-kit · 27 tokens

specify

Create or update the feature specification from a natural language feature description.

github/spec-kit · 13 tokens

analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

github/spec-kit · 26 tokens

converge

Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.

github/spec-kit · 35 tokens

implement

Execute the implementation plan by processing and executing all tasks defined in tasks.md.

github/spec-kit · 14 tokens