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 agentmods add skills/stjbrown/agent-knowledge/kb-visualizenpx skills add stjbrown/agent-knowledge --skill kb-visualizegit clone --depth 1 https://github.com/stjbrown/agent-knowledgeWhat 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 | $0.00029 | $0.01052 |
| Opus 5 | $0.00015 | $0.00526 |
| Sonnet 5 | $0.00006 | $0.00210 |
| Haiku 4.5 | $0.00003 | $0.00105 |
Grade A, and why
kb-visualize 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 2d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kb-visualize — see the bundle as a graph
Render a bundle as an interactive force-directed graph of its concepts, so a human can see its shape — hubs, clusters, orphans, and how concepts connect. You author the view from a deterministic graph model, so it can adapt to the request (a whole-bundle map, or a subgraph around one concept); it is not a fixed template.
1. Extract the graph model
Run the bundled extractor against the target bundle (default knowledge/). It is a zero-dependency
Node script (node >=18); <skill-dir> is this skill's directory — ${CLAUDE_SKILL_DIR} under
Claude Code, or whatever path your host exposes for the skill:
node "<skill-dir>/scripts/graph.mjs" <bundle-dir>
It prints JSON: nodes (including id, display metadata, status, generated, verified, derived
trust_tier, stale_after, derived is_stale, structured sources, attestation metadata, body,
links, and cited_by), the distinct types, and edges. Backlinks (cited_by) and
edges are already computed from the cross-links in concept bodies. If the user scoped the request to
one concept/area, filter the model to that node plus its neighbors.
The renderer MUST consume the model produced by this extractor invocation. Do not reuse a previous run's cached graph JSON or a generator hard-coded to another cache filename. If the host requires scratch files, overwrite one explicit model path, pass that same path to the renderer, and remove it after verification.
Completion criterion: you have the graph model, and (if scoped) filtered it to the requested subgraph.
2. Choose the output form by host capability
- Host renders interactive UI (e.g. Claude Desktop, Codex Desktop, an MCP-Apps host): render the graph as native UI so it's live in the conversation.
- Host is text/artifact only (e.g. Claude Code, a terminal): write a self-contained HTML file (single file, no backend, CDN libs only) next to the bundle or as an artifact, and give the user the path.
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.
- 2d ago First seen · 84 lines · 29 tokens per session scan A f573581586cc
kb-visualize is a skill published in the GitHub repository stjbrown/agent-knowledge (32 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 1,052 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
okf-authoring
Author Open Knowledge Format (OKF) bundles — knowledge represented as a directory of markdown files with YAML frontmatter. Use when asked to create, write, generate, enrich, or validate an OKF bundle or OKF concept docs; to turn a data source (Glue database, API, database, catalog), documentation, or a research topic…
refresh-okf-mcp-token
Fetch or refresh an OAuth2 access token for the OKF Data wiki consumption MCP server. Use when the OKF MCP server returns 401/403/unauthorized/expired-token errors, when the user asks to refresh, renew, or get a new OKF MCP token, or when setting up authentication to call the okf-mcp / okfconsumption MCP runtime.
report-authoring
The report-authoring methodology: required structure, language, evidence discipline, and figure selection. Read BEFORE your first createreport of a conversation - the tool validates shape; this is everything it cannot check.
setup
Set up the OKF MCP plugin — outputs a guide for the user to create their /.okf/credentials file with their OAuth2 client id/secret. Use when first enabling the plugin, when headersHelper fails with "Missing credentials", or when the user says "setup okf".
wegent-knowledge
Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).