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 skills add flsteven87/llm-wiki-mcp --skill wiki-ingestgit clone --depth 1 https://github.com/flsteven87/llm-wiki-mcpWrote 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/skills/flsteven87/llm-wiki-mcp/wiki-ingest)<a href="https://agentmods.dev/skills/flsteven87/llm-wiki-mcp/wiki-ingest"><img src="https://agentmods.dev/badge/skills/flsteven87/llm-wiki-mcp/wiki-ingest/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/skills/flsteven87/llm-wiki-mcp/wiki-ingest"><img src="https://agentmods.dev/badge/skills/flsteven87/llm-wiki-mcp/wiki-ingest.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 | $0.00267 | $0.01518 |
| Opus 5 | $0.00133 | $0.00759 |
| Sonnet 5 | $0.00053 | $0.00304 |
| Haiku 4.5 | $0.00027 | $0.00152 |
Grade A, and why
wiki-ingest 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 12d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki-ingest
Process a new source into an existing Karpathy-style LLM wiki. The pattern and the ingest example this skill follows are described in https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f.
Karpathy's ingest example, verbatim:
the LLM reads the source, discusses key takeaways with you, writes a summary page in the wiki, updates the index, updates relevant entity and concept pages across the wiki, and appends an entry to the log.
A single ingest may touch 10–15 pages. Karpathy prefers one source at a time with the user in the loop; batch mode is also possible (see the end).
Prerequisites
- A wiki exists. If not, run
wiki-initfirst. - The llm-wiki-mcp server is wired into this session. If
wiki_inventoryis not callable, tell the user to add the server to their MCP client config and restart.
Pre-flight
Read CLAUDE.md. This is the authoritative schema — page
categories, frontmatter fields, link conventions, and operation
vocabulary. The user may have evolved it since wiki-init. Honor
the current state, not the defaults.
Flow
Follow Karpathy's six actions in order.
1. Read the source
Use whatever the host agent provides — WebFetch for URLs, Read
for local files, or treat pasted text as-is. The llm-wiki-mcp server
does not fetch sources; extraction is the host's job. Archiving the
raw file into raw/ is the user's job, not this skill's.
2. Discuss key takeaways with the user
Surface the handful of entities, concepts, and claims that matter. Ask the user what to emphasize.
3. Write a summary page in the wiki
Pick a slug (lowercase, dashes, at least two characters). Build
body to match the schema in CLAUDE.md, including any
frontmatter block. The server does not validate frontmatter shape —
you are responsible for consistency.
wiki_write_page(slug=..., body=..., etag=None)
etag=None asserts the page does not exist. If the server returns
a conflict error, the slug is taken — pick a different one.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 142 lines · 267 tokens per session scan A 3f2500a481aa
wiki-ingest is a skill published in the GitHub repository flsteven87/llm-wiki-mcp (1 stars, last pushed 5mo ago), licensed MIT. It adds 267 tokens to every session and 1,518 once invoked, about $0.0013 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.