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.
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.
git clone --depth 1 https://github.com/nvk/llm-wikiWrote 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.
[](https://agentmods.dev/commands/nvk/llm-wiki/portfolio)<a href="https://agentmods.dev/commands/nvk/llm-wiki/portfolio"><img src="https://agentmods.dev/badge/commands/nvk/llm-wiki/portfolio/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.
<a href="https://agentmods.dev/commands/nvk/llm-wiki/portfolio"><img src="https://agentmods.dev/badge/commands/nvk/llm-wiki/portfolio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00020 | $0.00569 |
| Opus 5.5 | $0.00008 | $0.00228 |
| Sonnet 5.5 | $0.00004 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
portfolio 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your task
Build a current portfolio view across Ideas and Projects. Read
skills/wiki-manager/references/portfolio.md, plus ideas.md or projects.md
only when their derivation rules are needed.
This operation is read-only. It must not create a project-ideas topic, a hub
Ideas/Portfolio directory, saved view, duplicate record, or activity-log entry.
Resolve scope
Resolve HUB from $HOME/.config/llm-wiki/config.json, preferring hub_path.
--localselects the current.wiki/.--wiki <name>selects one active topic fromHUB/wikis.json.- With neither flag, select every active topic in
HUB/wikis.json, excluding the synthetichubentry. - Skip archived topics unless
--include-archivedis explicit.
Build the catalog
For each selected topic:
- Read its
_index.md. - Read
inventory/ideas/_index.mdwhen present. Open individual Idea records only for missing requested fields, stale-index checks, filters, project linkage, or maturity verification. - Enumerate active Projects from
output/projects/*/WHY.md. Read only the first heading and first non-heading paragraph by default. - Link an Idea and Project only through an explicit resolving
project:field. A linked Project has originpromoted Idea; every other Project has origindirect. Never infer lineage from matching slugs or titles. - Apply filters and limits after collecting the compact metadata.
Do not read raw/, full Concept/article bodies, loose outputs, or Project
member contents for the ordinary list.
Report
Show counts followed by separate compact Ideas and Projects tables. Include topic, canonical link/path, operational state, next action or goal, and explicit cross-links. State that Concepts are supporting knowledge rather than portfolio rows and that the result is derived live from topic-owned records.
If the user asks to discover legacy or Concept-derived opportunities, stop after a 1-3 candidate preview. Do not create bulk Idea records without explicit approval.
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.
- 1mo ago First seen · 54 lines · 20 tokens per session scan A 400e01f35cd4
portfolio is a command published in the GitHub repository nvk/llm-wiki (1,436 stars, last pushed 17d ago), licensed MIT. It adds 20 tokens to every session and 569 once invoked, about $0.0001 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.
Other commands, from other repositories
amend-plan
Plan Amend - Discuss and apply amendments to a plan.json implementation plan.
hep-graph.body
A command for viewing saved Agentlas automation graphs and requesting that one be run. The desktop app performs the actual run.
project-setup
Set up a new project from scratch with AI development resources, virtual environment, and project structure.
adr
Create an Architectural Decision Record (ADR) to document a significant technical decision.
issue-triage
Intelligent issue classification and triage.
checklist
Generate a custom checklist for the current feature based on user requirements.