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 saulmcphd/okf-skills --skill okf-dashboardgit clone --depth 1 https://github.com/saulmcphd/okf-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/saulmcphd/okf-skills/okf-dashboard)<a href="https://agentmods.dev/skills/saulmcphd/okf-skills/okf-dashboard"><img src="https://agentmods.dev/badge/skills/saulmcphd/okf-skills/okf-dashboard/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/saulmcphd/okf-skills/okf-dashboard"><img src="https://agentmods.dev/badge/skills/saulmcphd/okf-skills/okf-dashboard.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 | $0.00186 | $0.02239 |
| Opus 5 | $0.00093 | $0.01120 |
| Sonnet 5 | $0.00037 | $0.00448 |
| Haiku 4.5 | $0.00019 | $0.00224 |
Grade A, and why
okf-dashboard 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 10d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build an OKF dashboard (explore + ask)
Stand up the "use the brain" layer over an existing OKF bundle. Two halves — a graph explorer to see the brain and an ask-the-brain Q&A to query it. This skill is domain-agnostic: it works over any OKF bundle (gardening, academic, a company wiki), not one project.
A dashboard is a real piece of software — treat it as a build track, not a one-liner. But both halves read the same inputs the bundle already has: the typed markdown nodes, their frontmatter, and the markdown links between them. No database, no embedding store required.
Inputs (what both halves read)
- Nodes — the
*.mdfiles underconcepts/ entities/ playbooks/ references/ systems/. Each carries frontmatter (type,title,description,tags,provenance, …). - Edges — the bundle-relative markdown links in each node's body (
[Title](/concepts/concept-x.md)). This is the same edge sourcelint/graphuse. (Legacy[[wikilinks]]may also be parsed if present.) index.md— the curated navigation layer; the retrieval spine for ask-the-brain.
Part A — Graph explorer (see the brain)
If the bundle already has a generator, use it
If okf_tools.py is present, python okf_tools.py graph already writes a self-contained interactive
okf-graph.html (force-directed, coloured by type). That is the reference implementation — run it, or
copy/adapt it for a new bundle. okf_tools.py all also refreshes the index the graph relies on.
Building one from scratch (a bundle with no tooling)
Produce a single self-contained HTML file (inline the JS/CSS — no external CDN, so it stays as portable as the bundle itself). Two steps:
- Extract the graph data. Walk the node files; for each, emit a node record and parse its body for
markdown links to build edges:
{ "nodes": [ {"id": "/concepts/concept-companion-planting.md", "label": "Companion planting", "type": "concept", "tags": ["pest-control"], "in_degree": 5, "out_degree": 2, "description": "…", "human_verified": false} ], "edges": [ {"source": "/concepts/concept-companion-planting.md", "target": "/concepts/concept-crop-rotation.md"} ] } - Render it as a force-directed graph in one HTML file, colouring nodes by
type, sizing them by centrality, and drawing edges directed (an arrow from the linking node to the node it links).
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.
- 10d ago First seen · 147 lines · 186 tokens per session scan A ff57a4386275
okf-dashboard is a skill published in the GitHub repository saulmcphd/okf-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 186 tokens to every session and 2,239 once invoked, about $0.0009 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.