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 jame581/LogseqBrain --skill brain-loadgit clone --depth 1 https://github.com/jame581/LogseqBrainWrote 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/jame581/logseqbrain/brain-load)<a href="https://agentmods.dev/skills/jame581/logseqbrain/brain-load"><img src="https://agentmods.dev/badge/skills/jame581/logseqbrain/brain-load/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/jame581/logseqbrain/brain-load"><img src="https://agentmods.dev/badge/skills/jame581/logseqbrain/brain-load.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 | $0.00096 | $0.01348 |
| Opus 5.5 | $0.00038 | $0.00539 |
| Sonnet 5.5 | $0.00019 | $0.00270 |
| Haiku 4.5 | $0.00010 | $0.00135 |
Grade A, and why
brain-load scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 26d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brain Load
Running the helper
- Bash:
sh "<this skill's base directory>/../_shared/bin/brain" <command> … - PowerShell-only Windows:
& "$(Split-Path (Split-Path (Get-Command git).Source))\bin\bash.exe" "<base>/../_shared/bin/brain" <command> … - Neither works: stop and say "logseq-brain needs Git for Windows (Git Bash) — https://git-scm.com/download/win".
- In Cowork, always pass
--graph <connected folder>. Elsewhere pass--graphonly when the graph is not configured. It may go anywhere on the line. On exit 2 withgraph not resolved, followskills/_shared/path-resolution.md, then pass--graph. - Put text arguments in single quotes; a
'inside becomes'\''. In double quotes the shell runs backticks and expands$. - Exit 0 clean, 1 findings (act on them), 2 error (act on its reason; don't retry blindly). Quote every
coverage:line. Never recompute a figure it printed. Itsgraph:line is the folder for your own Read, Edit and Write calls.
Loading a project
- One call:
brain load <name>. Pass the user's words as-is. Don't list the graph first. Onpage not found, offer itsdid you mean:lines. Only when there are none, followreferences/matching.md. - Read its blocks:
map: staleormissing: say so, and state coverage fromcomputed:. Read-only: suggest a save, never write.drift:over 30 days: suggest a rebuild (skills/_shared/digest.md), never unprompted.staleness:aging: "Note: last updated N days ago."stale: "⚠ This project hasn't been updated in N days. Context may be outdated — verify before acting on it."abandoned: "This project is marked active but hasn't been touched in N days. Want to update it or mark it paused?"(no valid last-updated): suggest a brain-save to set one.freshandexempt: say nothing.== journal: today's notes on the page. Quote its coverage line.digest: missing: take the fallback.digest: not applicable: not a project page; read it with boundedbrain read/brain tail.== activity: already logged; don't log again.
- Stop reading. Don't pre-load sections, linked pages or task pages. Fetch more only on request, one level at a time, per
skills/_shared/escalation.md. - Active tasks: name the task IDs the digest mentions. Never read a task page's body.
- Continuity hint: "Picking up where you left off — focus: [focus]. Next: [next]. Open: [open]."
- Present, with what was not read. Give the name, status, staleness, the digest bullets and the hint. Then paraphrase the Map's
label | figureclauses:Loaded digest for Unicorn-Globus (active, updated 2026-09-07). Focus: … Next: … Not read: Session Log 151 KB (62 entries), Decisions 3 KB (3), Current Plan 3 KB, 7 smaller sections. Ask and I'll search any of it.
What ships with it
2 files 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.
- 26d ago Changed · -11 lines e0c1a29bf395
- 1mo ago Changed · -59 lines 6ce6268c38fe
- 1mo ago First seen · 134 lines · 96 tokens per session scan A 8d287f8ed490
brain-load is a skill published in the GitHub repository jame581/LogseqBrain (18 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 1,348 once invoked, about $0.0004 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
curator-continuity
Apply at the start of a build or coding session on a Curator-tracked project, and again as your own context fills, without waiting to be asked. Activates on "continue", "resume", "where did we leave off", "pick up where we left off", "what were we working on", "catch me up on this project", and on the save side "save…
my-curator
Use when interacting with the user's My Curator second brain via the my-curator MCP. Activates for READ ("what does my wiki say about X", "what do I know about X", "search my notes", "deep research my second brain", "find every source that mentions Y", "what does our cohort wiki say"), WRITE ("save to my wiki"…
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
memanto-companion
Inspect and manage the cross-session engineering memory that Memanto maintains for your Claude Code skills. Use when the user asks what Memanto remembers, wants to see their engineering profile, manually recall context for a skill, or store a decision. The automatic lifecycle hooks handle capture/injection on their…
openlore
Query and publish to an OpenLore knowledge repository over SSH using ordinary shell commands. Use when a task needs project documentation, runbooks, shared team knowledge, or a place to publish findings.
Context Doctor
Investigate and repair an agent's context — memory, system prompt, and skills — using observed behavior as evidence. Use when the user asks to audit, clean up, or fix your memory or context, or runs /doctor. Do not load for routine memory reads or edits, or requests that merely mention memory.