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-ingest-sourcegit 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-ingest-source)<a href="https://agentmods.dev/skills/saulmcphd/okf-skills/okf-ingest-source"><img src="https://agentmods.dev/badge/skills/saulmcphd/okf-skills/okf-ingest-source/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-ingest-source"><img src="https://agentmods.dev/badge/skills/saulmcphd/okf-skills/okf-ingest-source.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 | $0.00193 | $0.02376 |
| Opus 5 | $0.00097 | $0.01188 |
| Sonnet 5 | $0.00039 | $0.00475 |
| Haiku 4.5 | $0.00019 | $0.00238 |
Grade A, and why
okf-ingest-source 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ingest a new source into an OKF brain
The safe way to grow a brain from new material. Ingestion is integrate, not append, and it is human-gated: the agent proposes, a human decides, then the agent writes. A single source usually does several things at once — enrich a few existing nodes and spawn a new one. Domain-agnostic.
This is the detailed procedure behind the "Ingest" step of okf-create-bundle's maintenance loop, and the generic form of a project's ingestion plan (e.g.
plan.md§6B). Marie Haynes' public OKF brain implements the same "Review Proposed Changes → Approve/Reject" gate.
The loop: ASSESS → HUMAN APPROVES → ENRICH
1. Assess (automated proposal — nothing is written yet)
Read the whole source, then match its content against the existing brain via index.md (curated
navigation) and produce a per-item proposal:
- Enrich existing nodes — list each node the source strengthens and the specific
#section: fill a missing section or expand a thin one. Use okf-gap-scan to know which section of which node is incomplete. - New node(s) — genuinely new topics / people / sources the brain lacks (a new concept, entity, or —
for the source document itself — a
referencenode; see okf-node-types). - Fill known gaps (check the backlog). Cross-check the source against the standing missing-node
backlog from okf-gap-scan (its
candidate_nodes— topics your nodes already name but have no node of their own): for each candidate, ask whether this source carries enough to create that node now. This closes the loop — gap-scan finds what's missing, ingestion fills it the moment a source provides the material — so no upload is ever triaged in isolation from what you already know you're missing. - Contradictions — where the source disagrees with an existing claim, flag it (both statements, each dated and sourced) rather than silently overwriting.
Present it as a checklist the human can act on item-by-item, e.g.:
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 · 134 lines · 193 tokens per session scan A 42f90c9e6e54
okf-ingest-source is a skill published in the GitHub repository saulmcphd/okf-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 193 tokens to every session and 2,376 once invoked, about $0.0010 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.