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 TheSmuks/ai-project-template --skill llm-wikigit clone --depth 1 https://github.com/TheSmuks/ai-project-templateWrote 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/thesmuks/ai-project-template/llm-wiki)<a href="https://agentmods.dev/skills/thesmuks/ai-project-template/llm-wiki"><img src="https://agentmods.dev/badge/skills/thesmuks/ai-project-template/llm-wiki/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/thesmuks/ai-project-template/llm-wiki"><img src="https://agentmods.dev/badge/skills/thesmuks/ai-project-template/llm-wiki.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 | $0.00031 | $0.02157 |
| Opus 5.5 | $0.00012 | $0.00863 |
| Sonnet 5.5 | $0.00006 | $0.00431 |
| Haiku 4.5 | $0.00003 | $0.00216 |
Grade A, and why
llm-wiki 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.
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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Wiki
A pattern for building and maintaining a structured, interlinked collection of markdown files — a personal or team knowledge base — using LLM agents. The wiki is maintained incrementally alongside code work.
When to Use
Invoke this skill when you want to:
- Capture research, decisions, or references from web searches or documents into a persistent knowledge base
- Query accumulated knowledge to answer questions that require synthesizing multiple sources
- Maintain a log of what the wiki has grown to contain
- Onboard a new agent or human to a topic by pointing them at the wiki
The wiki is opt-in. Projects that don't need it are unaffected. Projects that do can build it up over time.
Setup
When activating this skill on a fresh project, create the wiki directory structure and seed files:
mkdir -p wiki raw
touch wiki/index.md wiki/log.md
wiki/index.md Template
# Wiki Index
> Content catalog for the LLM Wiki. Maintained by agents after each ingest operation.
## Topics
<!-- Add entries as you create pages:
- [[topic-name]] — Brief description
-->
## Recent Additions
<!-- Chronological list of new pages:
- [[YYYY-MM-DD]] [[page-name]] — Why it was added
-->
wiki/log.md Template
# Wiki Log
> Append-only chronological record of wiki operations. Never edit past entries.
## Usage
Each entry follows this format:
YYYY-MM-DD
ingest
- Sources:
- Pages created:
- Pages updated:
- Summary:
query
- Question:
- Answered by:
- Summary:
lint
- Issues found:
- Issues fixed:
- Summary:
---
## Architecture
The wiki operates in three layers:
┌─────────────────────────────────────────────────────────────┐ │ Raw Sources (immutable, timestamped inputs) │ │ raw/ │ │ PDFs, web captures, transcript files, etc. │ └─────────────────────────────────────────────────────────────┘ │ Ingest ▼ ┌─────────────────────────────────────────────────────────────┐ │ Wiki (LLM-maintained markdown pages) │ │ wiki/ │ │ Topic pages, concept notes, decision records, etc. │ │ Linked via [[wiki-links]] │ └─────────────────────────────────────────────────────────────┘ │ Synthesize ▼ ┌─────────────────────────────────────────────────────────────┐ │ Schema (instructions for AGENTS.md) │ │ Key facts, conventions, decisions that agents must follow │ └─────────────────────────────────────────────────────────────┘
### Raw Sources (`raw/`)
Immutable source material. Never edit after creation — this preserves provenance.
**Naming convention:**
YYYY-MM-DD-.
Example: `2024-01-15-attention-mechanism-paper.pdf`
### Wiki Pages (`wiki/`)
Markdown files maintained by agents. Organized by topic, linked via `[[double-bracket]]` links (standard in Obsidian, supported by most markdown link tools).
**Naming convention:**
-.md
Example: `attention-mechanism.md`, `transformers-vanishing-gradients.md`
**Frontmatter (required):**
```yaml
---
created: YYYY-MM-DD
updated: YYYY-MM-DD
tags: [tag1, tag2]
---
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 First seen · 387 lines · 31 tokens per session scan A fd66bc6907fa
llm-wiki is a skill published in the GitHub repository TheSmuks/ai-project-template (8 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 2,157 once invoked, about $0.0001 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.
Other skills, from other repositories
llm-wiki
Explain and apply the foundational LLM Wiki architecture and knowledge-management strategy. Use for setup, architecture, schema, or organization decisions; operational ingest/query/lint work uses dedicated skills.
wiki-lint
Audit wiki health: broken links, orphans, contradictions, stale content, lifecycle and tag issues. Use for maintenance or health checks. Default is report-only; use wiki-dedup for page-identity merges.
wiki-export
Export the Obsidian wiki graph to JSON, GraphML, Neo4j Cypher, Postgres/SQL, HTML, or OKF bundles. Use when transferring or visualizing wiki data in external tools; wiki-import handles the reverse direction.
wiki-query
Search and synthesize answers from the compiled Obsidian wiki, including cited and multi-hop answers. Use for questions about existing wiki knowledge or fast index-only lookups, and for challenge requests ("challenge this", "argue against X", "poke holes in my plan") that look for the vault's own evidence against a…
wiki-status
Report wiki ingestion/completeness state, pending source delta, structural insights, or maintenance equilibrium. Use for remaining-work/status questions, hubs and bridges, or whether maintenance skills still have pending changes. wiki-digest summarizes learned knowledge instead.
cross-linker
Find and add missing cross-references between wiki pages. Use when pages are disconnected or after large ingestion. This modifies pages to add links; use wiki-lint for report-oriented structural auditing.