What is llm-wiki-manager?

A manager for a personal software-development knowledge base made of structured Markdown files. It can ingest source material, answer questions from the stored knowledge, and maintain links and an index.

Use it to initialize a wiki, add articles or documents, query stored information, and maintain entries about architectures, technologies, decisions, problems, and solutions.

It keeps useful project knowledge from being scattered across separate documents or lost between sessions. Updating the index and cross-references makes the collection easier to use as it grows.

llm-wiki-manager — Skill for Claude Code and Codex by Tano73

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.

Any agent

npx skills add Tano73/agent-skills --skill llm-wiki-manager

Clone the repo

git clone --depth 1 https://github.com/Tano73/agent-skills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tano73/agent-skills/llm-wiki-manager/github.svg)](https://agentmods.dev/skills/tano73/agent-skills/llm-wiki-manager)

Your own site

<a href="https://agentmods.dev/skills/tano73/agent-skills/llm-wiki-manager"><img src="https://agentmods.dev/badge/skills/tano73/agent-skills/llm-wiki-manager/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tano73/agent-skills/llm-wiki-manager"><img src="https://agentmods.dev/badge/skills/tano73/agent-skills/llm-wiki-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 240 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,309 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00240	$0.02309
Opus 5.5	$0.00096	$0.00924
Sonnet 5.5	$0.00048	$0.00462
Haiku 4.5	$0.00024	$0.00231

Measured 1mo ago against content hash d52ba380ad69, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

llm-wiki-manager 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.

The scan reads SKILL.md. This mod also ships 8 executable files (scripts/raw_check.py, scripts/test_frontmatter_aliases.py, scripts/wiki_index.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/llm-wiki-manager/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Wiki Manager

You are a disciplined wiki maintainer, not a generic assistant. You keep a persistent, compounding knowledge base of Markdown files. The wiki is an OKF v0.2 bundle (Google's Open Knowledge Format) operated by Karpathy's LLM-wiki pattern: knowledge is compiled once and kept current, never re-derived on every query. The concept is in references/llm-wiki-karpathy.md; the storage contract is in references/okf.md.

Token discipline. Your bookkeeping is deterministic, so it runs in scripts, not in your head. You reason; the scripts file. Never hand-write wiki/index.md or wiki/log.md, and never compare raw content by eye.

Scripts

All under $HOME/.agents/skills/llm-wiki-manager/scripts/:

Script	Deterministic job	When to run
`wiki_index.py <root> --write\|--check`	Regenerates the catalog from page frontmatter / links	After any page change; `--check` in LINT
`wiki_log.py <root> append\|tail\|init`	Appends newest-first OKF log entries	After any operation that changed content
`raw_check.py <root> <file> [--stdin]`	SHA-256 versioning check for raw/ intake	Before writing ANY file into raw/
`wiki_search.py <root> <words...>`	Returns only the pages that match a query	QUERY, instead of opening whole pages
`wiki_sync.py <root> [--since R] [--write-marker]`	Gathers git commits + changed files since the last sync marker	SYNC, after implementation / PR merge
`wiki_lint.py <root> [--json] [--strict]`	Structural + OKF health checks	LINT; after SETUP

References (load on demand)

File	Read when
`references/llm-wiki-karpathy.md`	You need the why (user asks "how does this work?"); otherwise optional
`references/okf.md`	Creating/editing pages, configuring a wiki — the frontmatter contract, templates, index/log formats
`references/setup-ingest.md`	Running SETUP or INGEST — step-by-step, incl. `raw_check.py` intake rules
`references/query.md`	Answering a question — wiki → DocMind → GitHub issues → permissioned fallback
`references/lint.md`	Auditing the wiki — mechanical + semantic categories, report template, modes
`references/sync.md`	Post-implementation SYNC — git-diff-driven updates, verified-page gate, project hook
`references/docmind.md`	DocMind is available and the operation touches it (SPEC-DRAFT/COMPOUND, PROMOTE, DocMind ingest, full LINT)

Read the full file on GitHub · 159 lines

Files

What ships with it

17 files 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.

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.

1mo ago Changed · -208 lines d52ba380ad69
1mo ago Changed · +6 lines b0bf96299199
1mo ago Changed · -251 lines · +36 tokens per session 9f8f06048175
2mo ago First seen · 612 lines · 204 tokens per session scan A f70aa1b79765

Subscribe to this mod's changes

llm-wiki-manager is a skill published in the GitHub repository Tano73/agent-skills (2 stars, last pushed 23d ago), licensed MIT. It adds 240 tokens to every session and 2,309 once invoked, about $0.0010 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 2026-08-31.

Memory and context

knowledge-ingest

Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, source notes, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…

openclaw/openclaw · 80 tokens

mem0-oss-to-platform

Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…

mem0ai/mem0 · 217 tokens

forget

Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…

asgeirtj/system_prompts_leaks · 74 tokens

Cortex

LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…

danielmiessler/LifeOS · 184 tokens

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.

opensquilla/opensquilla · 44 tokens

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…

shiwenwen/hope-agent · 115 tokens