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/ingestgit 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/ingest)<a href="https://agentmods.dev/commands/nvk/llm-wiki/ingest"><img src="https://agentmods.dev/badge/commands/nvk/llm-wiki/ingest.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.03038 |
| Opus 5 | $0.00017 | $0.01519 |
| Sonnet 5 | $0.00007 | $0.00608 |
| Haiku 4.5 | $0.00003 | $0.00304 |
Grade A, and why
ingest scanned grade A 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Read, Write, Edit, Glob, Grep, Bash(ls:*), Bash(wc:*), Bash(date:*), Bash(mv:*), Bash(mkdir:*), Bash(basename:*), Bash(file:*), Bash(curl:*), Bash(mktemp:*), Bash(rm:*), Bash(pdftotext:*), Bash(python3:*), How it starts
The opening of the file, as written. The whole thing — 204 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 and--new-topic <name>is set → create the topic wiki (see below). If missing and no--new-topic→ stop with "No wiki found. Use--new-topic <name>to create one, or run/wiki initfirst."
Read the ingestion protocol at skills/wiki-manager/references/ingestion.md and the structure spec at skills/wiki-manager/references/wiki-structure.md. Then ingest source material.
Collection handoff
If the user is trying to import a bounded upstream corpus rather than one source
item, stop and hand off to /wiki:ingest-collection with the same wiki flags.
Signals include: "import wiki", "mirror wiki", "bulk ingest", "ingest
collection", "ingest repo", "import repo", "split CSV into messages", "Wayback
snapshots", MediaWiki dumps (.xml, .xml.bz2, .xml.gz), MediaWiki
api.php, CDX API URLs, or a GitHub/GitLab repo plus words like "all", "docs",
"BIPs", "wiki", or "collection".
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.
- 4d ago First seen · 204 lines · 34 tokens per session scan A 225796c628b8
ingest is a command published in the GitHub repository nvk/llm-wiki (1,188 stars, last pushed 7d ago), licensed MIT. It adds 34 tokens to every session and 3,038 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
mempalace-status
Show the current state of your memory palace — wings, rooms, drawer counts, and suggestions.
review
Review the current diff against project memory.
gen-plan
Generate implementation plan from draft document.
speckit.archive
Archive a feature specification into main project memory after merge, resolving gaps and conflicts.
ingest-l1
L1 analysis loop for the abapwiki knowledge base: for each batch it launches the abap-analyzer sub-agent in parallel, then the adversarial judge abap-deepcheck (separate session), applies only the analyses that pass the fail-closed gate, and commits. Resumes exactly after an interruption. Use this skill to document…
knowledge-transfer
Interview a person to capture their operating know-how (tacit knowledge) and write it into the workspace as the company brain: processes, rules with source, glossary, decisions and open questions. For onboarding, a key person leaving, or standardizing a process.