A command for creating an implementation plan from research in an active wiki. It resolves the relevant knowledge base, asks about requirements, researches missing details, and produces a phased plan with supporting wiki references.

It is for planning software changes, researching open design questions, defining phases, and documenting decisions based on the project's existing knowledge base.

It turns scattered requirements and internal notes into an ordered plan with architecture decisions and evidence. This helps identify missing information before implementation begins.

plan — Command for Claude Code by nvk/llm-wiki

About the project

LLM Wiki is a system that uses AI agents to research sources, compile knowledge bases, organize project briefs, and answer questions from the resulting wiki. It is used to turn rough ideas and investigations into structured, reusable knowledge for agents, including Claude Code, Codex, and OpenCode. The catalogue entries are commands, hooks, skills, instructions, and a plugin that implement its workflow.

nvk/llm-wiki · 1,510 stars · on GitHub · llm-wiki.net

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.

Clone the repo

git clone --depth 1 https://github.com/nvk/llm-wiki

Made for: Claude Code.

Or install wiki, the plugin that ships this one along with the rest of its 1 skill, 28 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/nvk/llm-wiki/plan/github.svg)](https://agentmods.dev/commands/nvk/llm-wiki/plan)

Your own site

<a href="https://agentmods.dev/commands/nvk/llm-wiki/plan"><img src="https://agentmods.dev/badge/commands/nvk/llm-wiki/plan/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/nvk/llm-wiki/plan"><img src="https://agentmods.dev/badge/commands/nvk/llm-wiki/plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,754 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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.02754
Opus 5.5	$0.00016	$0.01102
Sonnet 5.5	$0.00008	$0.00551
Haiku 4.5	$0.00004	$0.00275

Measured 2mo ago against content hash 069068648121, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

plan 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 2mo 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.

claude-plugin/commands/plan.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your task

Resolve the wiki. Do NOT search the filesystem or read reference files — follow these steps:

Read $HOME/.config/llm-wiki/config.json. If it has hub_path, expand leading ~ only (not tildes in com~apple~CloudDocs) and prefer that path; use resolved_path only as a fallback cache when the expanded hub_path is unavailable and resolved_path is initialized. If config has only resolved_path, use it. If the configured path can be statted but reading wikis.json or listing topics/ fails with Operation not permitted, stop and ask the user to grant Full Disk Access/iCloud Drive access to the launcher; do not fall back to ~/wiki or resolved_path. Do not write machine-specific resolved_path into shared configs.
If no config → read $HOME/wiki/_index.md. If it exists → HUB = $HOME/wiki. If nothing found, ask the user where to create the wiki.
Wiki location (first match): --local → .wiki/ in CWD; --wiki <name> → HUB/wikis.json lookup with portable path resolution (<HUB>, ~, absolute, or HUB-relative); if the registry path is stale, fall back to HUB/topics/<name>; CWD has .wiki/ → use it; else → HUB.
Read <wiki>/_index.md to verify. If missing → stop with "No wiki found (or no articles). Run /wiki init and /wiki:research first to build a knowledge base."

Generate an implementation plan for what the user wants to build, grounded in the wiki's accumulated research. Follow the 6-stage pipeline below.

Inventory awareness: use active inventory records as planning constraints when they are relevant to the goal, especially blocked tasks, candidate corpora, open questions, and watch items. If the plan creates a durable work queue, suggest inventory records or a saved inventory view and show a sample before creating them. Keep project rationale in WHY.md; inventory is for trackable items and next actions.

Parse $ARGUMENTS

goal: What to build — everything that is not a flag. This is the planning objective.
--wiki : Target a specific topic wiki as the primary knowledge source (subject matter)
--with : Load a supplementary wiki as additional context. The primary wiki provides domain knowledge (what to build); --with wikis provide craft/skill knowledge (how to build it, writing techniques, design patterns). Multiple --with flags allowed.
--local: Use project-local .wiki/
--include-archived: Explicitly allow archived primary or supplementary wiki context. Label archived-derived constraints/sources in the plan.
--quick: Skip interview and gap research — produce a plan directly from wiki content (Stage 1 → Stage 5)
--no-interview: Skip the interview stage (Stage 2)
--no-research: Skip gap research (Stage 3) — plan only from existing wiki content
--format: Output structure. One of:
- roadmap (default) — phased implementation plan with timeline
- rfc — Request for Comments format (Google/Uber style: context, goals, design, alternatives)
- adr — Architecture Decision Record (context, decision, consequences per choice)
- spec — Technical specification (architecture, APIs, data models, testing)

Read the full file on GitHub · 256 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.

2mo ago First seen · 256 lines · 40 tokens per session scan A 069068648121

Subscribe to this mod's changes

plan is a command published in the GitHub repository nvk/llm-wiki (1,510 stars, last pushed 12d ago), licensed MIT. It adds 40 tokens to every session and 2,754 once invoked, about $0.0002 per session on Opus 5.5. 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.

Claude Code LLM Planning agentic-ai agentic-skills agentic-workflow codex

plan next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
plannvk/llm-wiki	Command	1.5k	12d ago	MIT	A	40	Claude Code
orchestrateruvnet/ruflo	Command	81k	yesterday	MIT	A	0	Claude Code
projectmodu-ai/moai-adk	Command	1.3k	3d ago	Apache-2.0	A	19	Claude Code
export-closedloop-learningsclosedloop-ai/claude-plugins	Command	123	today	Apache-2.0	A	13	Claude Code
performance-bottlenecksruvnet/ruflo	Command	81k	yesterday	MIT	A	0	Claude Code
test-featureLykhoyda/rn-dev-agent	Command	20	12d ago	MIT	A	30	Claude Code
specifyqarium/goga	Command	43	5d ago	BSD-3-Clause	A	0	Claude Code