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 po4yka/llm-wiki-skills --skill llm-wiki-threat-modelgit clone --depth 1 https://github.com/po4yka/llm-wiki-skillsWrote 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/po4yka/llm-wiki-skills/llm-wiki-threat-model)<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-threat-model"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-threat-model/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/po4yka/llm-wiki-skills/llm-wiki-threat-model"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-threat-model.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 | $0.00080 | $0.01570 |
| Opus 5.5 | $0.00032 | $0.00628 |
| Sonnet 5.5 | $0.00016 | $0.00314 |
| Haiku 4.5 | $0.00008 | $0.00157 |
Grade A, and why
llm-wiki-threat-model 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM-Wiki Threat Model
Goal
Produce a threat model for an LLM-Wiki system that maps trust boundaries, attack surfaces, prioritized threats, controls, CI gates, red-team scenarios and incident response.
Use references/docs/19-security-threat-model.md as the reference architecture and control baseline.
When to use
- The user asks for a STRIDE, LINDDUN, PASTA, or data-flow-diagram threat model of an LLM-Wiki system.
- The user wants trust boundaries, attack-surface mapping, abuse cases, or a risk/severity matrix for ingestion, retrieval, MCP/API, or write paths.
- The user is designing or hardening a new LLM-Wiki deployment (local-first, hosted, MCP/API server) and needs a control baseline and red-team scenarios before build-out.
- The user asks for an incident-response plan or security scorecard tied to a threat model, not an ad-hoc config review.
- Route requests to review an existing config or deployment for known weaknesses to
llm-wiki-security-reviewinstead; use this skill for building the formal model from scratch.
Inputs
- Implementation family: local-first, desktop app, repo-docs, Obsidian, team wiki, hosted product, MCP/API server.
- Data flows: capture, ingestion, raw storage, wiki compilation, indexing, retrieval, generation, MCP/API, writes, exports, observability.
- Data classes: public, internal, sensitive, regulated, unknown.
- Deployment: local stdio, localhost HTTP, remote MCP/API, CI, cloud models, cloud parsers, hosted search/vector DB.
- Existing controls: CODEOWNERS, branch protection, scanners, auth, review queue, audit logs, redaction, eval/red-team.
- Desired output: high-level model, detailed matrix, remediation plan, repo file changes or CI templates.
Procedure
1. Inventory components and data flows
Map:
sources -> ingestion/parsing -> raw store -> wiki pages -> indexes -> retrieval -> agent -> MCP/API tools -> proposals/PRs -> exports/traces
For each component, record:
component: ""
inputs: []
outputs: []
trusted: true|false
contains_sensitive_data: true|false
writes_durable_state: true|false
network_exposed: true|false
existing_controls: []
missing_controls: []
What ships with it
7 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.
- references/docs/19-security-threat-model.md 23 KB
- references/policies/redaction-retention-policy.md 3.7 KB
- references/policies/review-incident-response.md 3.1 KB
- references/templates/llm-wiki-security.github-actions.yml 2.9 KB
- references/templates/mcp-security-profile.yaml 3.6 KB
- references/templates/promptfoo-llm-wiki-redteam.yaml 3.8 KB
- references/templates/security-scorecard.yaml 4.0 KB
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 · 201 lines · 80 tokens per session scan A c9563d95bd3b
llm-wiki-threat-model is a skill published in the GitHub repository po4yka/llm-wiki-skills (4 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 1,570 once invoked, about $0.0003 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
obsidian-memory
Explicit-only Obsidian memory workflow. Use when the user explicitly asks to work with an Obsidian vault, LLM wiki, agent memory, RAW/source ingest, provenance, QUERY, LINT, or release safety for a markdown knowledge system. Do not auto-route ordinary coding sessions into external vault workflows.
wiki-lint
Health-check a wiki vault. Finds orphan pages (no inbound links), dead wikilinks (point to non-existent pages), missing frontmatter fields, stale claims, empty sections, and pages absent from catalog.md. Produces a structured report with severity tiers and proposes concrete fixes — but does not auto-apply them unless…
okf-harness-bootstrap
This unified entrypoint routes setup and workspace maintenance without making the user choose a mode.
meta-sync-template
Interactive flow to propagate the reference (.template) vault's plugins, snippets, and root docs to one or more configured vaults. Reads the active router config, lists every vault with online status, flags vaults missing obsidian-local-rest-api upfront, lets the user pick all or a subset, and optionally re-clones…
save
File the current Claude conversation (or a specific insight from it) as a structured wiki note. Auto-detects the right type (decision, answer, session-log, technique, ADR), writes appropriate frontmatter, places the file in the correct wiki folder, and updates catalog.md, journal.md, hot.md. Use when the user says…
librarian
Orchestrate vault knowledge workflows using the Librarian MCP server. Ingest solutions, search prior art, explore the knowledge graph, log daily learnings.