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-gap-scangit 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-gap-scan)<a href="https://agentmods.dev/skills/saulmcphd/okf-skills/okf-gap-scan"><img src="https://agentmods.dev/badge/skills/saulmcphd/okf-skills/okf-gap-scan/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-gap-scan"><img src="https://agentmods.dev/badge/skills/saulmcphd/okf-skills/okf-gap-scan.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 | $0.00219 | $0.02624 |
| Opus 5 | $0.00110 | $0.01312 |
| Sonnet 5 | $0.00044 | $0.00525 |
| Haiku 4.5 | $0.00022 | $0.00262 |
Grade A, and why
okf-gap-scan 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.
Scan an OKF brain for gaps
A completeness audit. This is distinct from link-lint (orphans / missing frontmatter / broken links,
handled by okf_tools.py lint): gap-scan asks "what knowledge is missing or thin?" — both within
nodes (incomplete sections) and across the brain (topics with no node at all). Output is a ranked
enrichment backlog. Domain-agnostic; this is the generic form of a project's gap plan (e.g. plan.md
§6C).
Gap type 1 — Structural completeness (section-schema check)
Define the canonical # sections expected of each node type, then score every node against its
schema, flagging missing sections (a gap to fill) and thin sections (a gap to enrich).
A reasonable default schema (adjust per bundle/domain):
| Type | Expected # sections |
|---|---|
concept |
# Definition, topic sections, # Evaluation (balanced criticisms), # Related, # References (or frontmatter sources: — OKF v0.2) |
entity |
# Definition, # Key contributions, # Significance, # Related, # References |
reference |
# What it is, # What this brain draws from it, # Where it lives, # Related |
playbook |
# Goal, # Inputs → Outputs, # Steps, # How to judge, # Guardrails, # Hand-off |
Score each node → {node, missing: [...], thin: [...]}. "Thin" = a section present but far below the
depth bar (e.g. a # Evaluation with one line). Rank by centrality (well-linked hubs first) and, if
you have it, traffic.
Gap type 2 — Coverage (missing nodes)
Topics the brain should have but doesn't. Strongest signals first:
- Named-but-nodeless (strongest — the brain's own writing implies the gap). A person/theory/source
the prose names (or a
# Referencessurname) with no matching node. High precision: if 20 nodes mention someone with no entity node, they deserve one. - Broken / absent internal links — a
[Title](/…/x.md)whose target doesn't exist yet (the spec tolerates these as "not-yet-written knowledge"; gap-scan turns them into a to-do). - External-hub diff (discovery lens ONLY). Crawl an authoritative hub for the domain (e.g. a Wikipedia category, a syllabus, a source's index) and diff its topic list against live nodes to surface structurally-important missing concepts, ranked by centrality.
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 · 219 tokens per session scan A b47d742a34a8
okf-gap-scan is a skill published in the GitHub repository saulmcphd/okf-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 219 tokens to every session and 2,624 once invoked, about $0.0011 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.