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 imphillip/gbrain-openclaw --skill ingestgit clone --depth 1 https://github.com/imphillip/gbrain-openclawWrote 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/imphillip/gbrain-openclaw/ingest)<a href="https://agentmods.dev/skills/imphillip/gbrain-openclaw/ingest"><img src="https://agentmods.dev/badge/skills/imphillip/gbrain-openclaw/ingest/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/imphillip/gbrain-openclaw/ingest"><img src="https://agentmods.dev/badge/skills/imphillip/gbrain-openclaw/ingest.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 | $0.00037 | $0.00766 |
| Opus 5.5 | $0.00015 | $0.00306 |
| Sonnet 5.5 | $0.00007 | $0.00153 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
gbrain-ingest 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ingest Skill
Workflow
-
Read the source. Meeting transcript, article, document, conversation log. Identify: participants, companies, topics, decisions, action items.
-
For each entity mentioned:
gbrain search "<name>"— does a page exist?- If yes:
gbrain get <slug>to read current compiled_truth. Rewrite State section with new info. Append to timeline.cat updated.md | gbrain put <slug>with updated content. - If no: Create page using the appropriate template (see Page Templates below).
cat new.md | gbrain put <slug>with new content.
-
Extract and create links.
- For every entity-to-entity reference in the source:
gbrain link <from> <to> --context "the sentence containing the reference" - Links are stored directionally. Create both directions if both pages exist and the relationship is mutual.
- For every entity-to-entity reference in the source:
-
Parse timeline entries.
- For each datable event:
gbrain timeline-add <slug> --date YYYY-MM-DD --summary "one line" --source "meeting/doc-ref"
- For each datable event:
-
Tag appropriately.
gbrain tag <slug> <tag>— use lowercase, hyphenated tags (e.g. yc-alum, investor, active-deal)
-
Verify.
gbrain stats— confirm page counts look right.gbrain get <slug>— spot-check a few pages.
Entry criteria
Not everything gets a page. The bar:
- Anyone you met 1:1 or in a small group: YES
- People discussed in substantive context: YES
- Companies in deal or investment context: YES
- Concepts worth tracking: YES
- Casual passing mentions with no substance: NO
Page templates
Person
---
title: Full Name
type: person
tags: []
linkedin: ""
twitter: ""
---
# Full Name
> One-sentence summary of who this person is and why they matter.
## State
Current role, company, location. What's relevant right now.
## Background
Education, career arc (condensed).
## Open Threads
- [ ] Action items or follow-ups
---
## Timeline
- **YYYY-MM-DD** | source — What happened.
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 · 113 lines · 37 tokens per session scan A efafaab665cd
gbrain-ingest is a skill published in the GitHub repository imphillip/gbrain-openclaw (11 stars, last pushed 6mo ago), licensed MIT. It adds 37 tokens to every session and 766 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
my-wiki
A skill for managing a local Markdown knowledge vault that stores captured webpages, PDFs, Office files, notes, images, folders, and ZIP files. It links preserved source material, called References, to durable topic pages, called Concepts.
vault-summarize
Use when the user asks to summarize, digest, or get an overview of a folder, project, or set of notes in their markdown vault — runs the vault's batched map-reduce recipe so note bodies stay out of the retained conversation context.
vault-workflow
Use when the user asks you to search, read, or reason about notes in their markdown vault — guides when to use which vault tool and how to chain them for good results.
kb
Set up, evolve, or operate a hraness/kb local-first Markdown knowledge base for coding-agent memory. Use when a user asks to design KB conventions or a recurring KB ritual; search or query a KB or Obsidian vault; load or recover repository context, plans, decisions, concepts, backlinks, semantic search, or Git…
manas-answer
Answer a personal-brain question through configured local Manas generation with verified citations and explicit evidence gaps.
manas-capture
Persist a user-authorized personal memory in Manas with provenance and a deduplicated write receipt.