A project manager for a topic wiki, where a wiki is a collection of organized notes and files. Each project is a folder that groups related outputs and records its purpose in a WHY.md file.

Use it to create and manage wiki projects containing playbooks, images, code, data, and other related outputs.

It keeps files made for one goal together and preserves the reason the project exists, so related work is easier to find and understand.

project — Command by nvk

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/nvk/llm-wiki/project

Clone the repo

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

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,508 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.00036	$0.02508
Opus 5	$0.00018	$0.01254
Sonnet 5	$0.00007	$0.00502
Haiku 4.5	$0.00004	$0.00251

Measured 2d ago against content hash 397a12c18de1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

project scanned grade C with 1 finding 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

**Removed in v0.2 simplification**: `focus`, `unfocus`, `retract`, `rename`. See `references/projects.md` § "Focus" for the rationale on dropping focus (pass `--project <slug>` explicitly instead). Rename and retract are

claude-plugin/commands/project.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your task

Manage projects — folders inside a topic wiki's output/projects/ directory that group related outputs. The only required file in a project is WHY.md, which captures the goal/rationale in plain markdown.

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 if found. Variant: wiki-neutral — see deviation below for the step-4 fallback.

Archive rule: topic archive and project archive are different layers. Project commands operate on active topic wikis by default. If --wiki <name> resolves to a topic under topics/.archive/, stop and ask the user to restore the topic or rerun with --include-archived; explicit archived operations must stay inside that archived topic path. The project subcommand archive <slug> only moves output/projects/<slug> inside the selected topic wiki.

Read the projects architecture at skills/wiki-manager/references/projects.md for the full rationale — particularly why WHY.md is the only required file (it holds the precious, non-derivable rationale) and why everything else is derived from filesystem state.

Idea awareness: if the user says "turn this Idea into a Project," "approve the brief," or equivalent, route to the Idea promotion workflow in skills/wiki-manager/references/ideas.md. Promotion freezes BRIEF.md and cross-links the records. Keep project new available for direct Projects that do not originate as Ideas.

Inventory awareness: projects group outputs around a goal; inventory tracks durable items with status, priority, and next action. If the user asks for a project backlog, source queue, watch list, or task list, suggest inventory records or a saved inventory view linked from the project instead of putting tracking state directly in WHY.md.

Read the full file on GitHub · 186 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.

2d ago First seen · 186 lines · 36 tokens per session scan C 397a12c18de1

Subscribe to this mod's changes

project is a command published in the GitHub repository nvk/llm-wiki (1,175 stars, last pushed 5d ago), licensed MIT. It adds 36 tokens to every session and 2,508 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

LLM Project management agentic-ai agentic-skills agentic-workflow claude-code codex

project

Getting it into your agent

What it costs to keep this loaded

Grade C, and why

Recursive force deletehighDestructive command

How it starts

Your task

What this file has done since we first saw it

Other commands, from other repositories

feedback

todo

story-implement

planning

story-new

cycle-complete