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.
npx agentmods add commands/nvk/llm-wiki/outputgit clone --depth 1 https://github.com/nvk/llm-wikiWhat 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 | $0.00033 | $0.01730 |
| Opus 5 | $0.00016 | $0.00865 |
| Sonnet 5 | $0.00007 | $0.00346 |
| Haiku 4.5 | $0.00003 | $0.00173 |
Grade A, and why
output 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 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.
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 — 103 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 hashub_path, expand leading~only (not tildes incom~apple~CloudDocs) and prefer that path; useresolved_pathonly as a fallback cache when the expandedhub_pathis unavailable andresolved_pathis initialized. If config has onlyresolved_path, use it. If the configured path can be statted but readingwikis.jsonor listingtopics/fails withOperation not permitted, stop and ask the user to grant Full Disk Access/iCloud Drive access to the launcher; do not fall back to~/wikiorresolved_path. Do not write machine-specificresolved_pathinto 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.jsonlookup with portable path resolution (<HUB>,~, absolute, or HUB-relative); if the registry path is stale, fall back toHUB/topics/<name>; CWD has.wiki/→ use it; else → HUB. - Read
<wiki>/_index.mdto verify. If missing → stop with "No wiki found (or no articles). Run/wiki initand/wiki:compilefirst."
Generate an output artifact from wiki content based on $ARGUMENTS.
Inventory and collect awareness: if the requested output is really a durable
queue, candidate list, watch list, source backlog, or next-action table,
recommend /wiki:inventory instead of creating another loose output. If the
request needs web discovery plus a catalog of artifacts, examples, memes,
media, tools, entities, or source candidates, recommend /wiki:collect
instead. If an output report discovers durable follow-ups, include a short
"Inventory candidates" section with a sample shape and ask before creating
records. Do not bury ongoing tracking state in a generated report.
Parse $ARGUMENTS
- type (required): One of:
summary,report,study-guide,slides,timeline,glossary,comparison. Use/wiki:collectfortype: collectioncatalogs because those require discovery, dedupe, media policy, and inventory fit checks. - --topic : Focus on a specific topic or concept (matches against tags and titles)
- --sources : Comma-separated list of specific wiki article paths to use
- --with : Load a supplementary wiki as additional context. The primary wiki (
--wiki) provides the subject (what to write about);--withwikis provide craft/skill knowledge (how to write it). Multiple--withflags allowed. Example:--wiki quantum-computing --with article-writinguses quantum-computing for domain content and article-writing for structure, hooks, and writing techniques. - --retardmax: Ship it NOW. Don't agonize over structure or completeness. Generate a rough-but-useful output fast, covering everything the wiki has. Better to have something imperfect now than something perfect never.
- --include-archived: Explicitly allow archived primary or supplementary wiki context. Label archived-derived material in the generated output.
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 · 103 lines · 33 tokens per session scan A 986a467b7316
output is a command published in the GitHub repository nvk/llm-wiki (1,175 stars, last pushed 5d ago), licensed MIT. It adds 33 tokens to every session and 1,730 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 2026-08-30.
Other commands, from other repositories
implement
Execute phased implementation with validation gates.
loop
Iteratively fix issues until all resolved or max iterations reached.
project
Generate project documentation (product.md, structure.md, tech.md, codemaps/).
review
Code review with security and @MX tag compliance check.
status
Show current Craft progress — cycles, stories, backlog in a rich dashboard view.
story-implement-auto
Autonomous story implementation — auto-picks stories, chains through cycle, no interactive prompts.