Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Tano73/agent-skillsnpx agentmods add skills/tano73/agent-skills/llm-wiki-managerWrote 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/tano73/agent-skills/llm-wiki-manager)<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.
<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>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 | $0.03975 |
| Opus 5 | $0.00120 | $0.01988 |
| Sonnet 5 | $0.00048 | $0.00795 |
| Haiku 4.5 | $0.00024 | $0.00398 |
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 6d 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 — 361 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. Your job is to write, update, and maintain a persistent, compounding knowledge base of Markdown files. Every source you ingest and every question you answer makes the wiki richer for future sessions. You keep cross-references consistent, never forget to update the index, and can touch 15 files in one pass.
The wiki specializes in software development knowledge: projects, architectures, technologies, frameworks, patterns, decisions, processes, problems and solutions.
Scripts: $HOME/.agents/skills/llm-wiki-manager/scripts/wiki_lint.py
References (load on demand):
references/llm-wiki-karpathy.md— Karpathy's LLM wiki pattern (why this works). Read if the user asks "how does this work?" / "what's the idea behind this?".references/docmind.md— DocMind integration (ingest/search, SPEC-DRAFT, SPEC-COMPOUND, PROMOTE, DocMind-aware LINT). Read whenever DocMind tools are available and the current operation needs them. Skip entirely in local-only mode.
Session Start
Locate the wiki root
Search for an existing wiki before assuming SETUP is needed. Prefer the first hit:
- Current working directory (look for
wiki/index.mdor a wiki-styleAGENTS.mdnext towiki/) - Parent directories up to 3 levels
- Common paths:
./knowledge/,./kb/,./wiki/,~/kb/,~/notes/,~/Documents/kb/ - If the user named an explicit path, use that
A directory is a wiki root when it contains wiki/index.md (preferred) or both wiki/ and raw/.
If a wiki is found
- Read
wiki/index.md(catalog). - Read the last 5 entries of
wiki/log.md(recent activity) — e.g.grep '^## \[' wiki/log.md | tail -5. - Briefly summarize: "Il wiki in
<root>contiene X entity, Y concept, Z sources. Ultima attività: ..." - If the user already stated an operation (ingest, query, lint, setup, spec, promote…) → go straight to that operation. Do not show the menu.
- Only if the intent is unclear → ask: SETUP · INGEST · QUERY · LINT (plus DocMind ops if tools are available).
What ships with it
5 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.
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.
- 6d ago Changed · -251 lines · +36 tokens per session 9f8f06048175
- 10d ago First seen · 612 lines · 204 tokens per session scan A f70aa1b79765
llm-wiki-manager is a skill published in the GitHub repository Tano73/agent-skills (2 stars, last pushed 7d ago), licensed MIT. It adds 240 tokens to every session and 3,975 once invoked, about $0.0012 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…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.