GBrain is a memory and retrieval layer for AI agents that searches, connects, and synthesizes information from stored sources. It is used to give coding agents and autonomous agents access to knowledge beyond their current code, including shared company information with access controls. The catalogue add-ons help agents operate GBrain and connect it to agent workflows.
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 agentmods add skills/garrytan/gbrain/eiirpnpx skills add garrytan/gbrain --skill eiirpgit clone --depth 1 https://github.com/garrytan/gbrainWrote 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/garrytan/gbrain/eiirp)<a href="https://agentmods.dev/skills/garrytan/gbrain/eiirp"><img src="https://agentmods.dev/badge/skills/garrytan/gbrain/eiirp.svg" alt="Measured on agentmods" 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 | $0.00182 | $0.05169 |
| Opus 5 | $0.00091 | $0.02584 |
| Sonnet 5 | $0.00036 | $0.01034 |
| Haiku 4.5 | $0.00018 | $0.00517 |
Grade A, and why
eiirp 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 6d 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 — 531 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EIIRP — Everything In Its Right Place
"Everything in its right place" — Radiohead, Kid A
Contract
After any significant work, EIIRP organizes ALL outputs across two domains:
Knowledge domain (brain):
- Every piece of knowledge lands in the correct brain location.
- All sources are cited and linked.
- The active schema pack is updated if a new content type emerged.
- Entity pages created/updated with cross-links.
Capability domain (skills): 5. Every reusable pattern becomes a composable skill. 6. Existing skills are audited for DRY violations. 7. Skill graph is MECE — no gaps, no overlaps, no ambiguous routing.
The meta-guarantee: Nothing produced during significant work lives only in chat. Knowledge → brain. Patterns → skills. Everything in its right place.
When to Use
- After completing a deep research thread.
- After building something new (code, pipeline, workflow).
- After a multi-source analysis that produced significant findings.
- When the user says "EIIRP", "organize this", "DRY this up", "make this re-doable".
- When a work session produced both knowledge AND new capabilities.
- When you notice skill overlap, duplication, or gaps.
Auto-Fire Gate — file before you deliver (ALWAYS-ON)
Convention: see conventions/brain-first.md — this is its write side. Substantial analysis belongs in the brain, not only in chat.
Unlike the 7-phase audit above (which the user invokes after a work
session), this gate is an always-on agent-side convention, like
signal-detector: the agent applies it on every substantive reply, not
when a trigger phrase routes here. Always-on is a harness-routing
convention that a well-behaved agent follows — not a mechanical
guarantee; nothing in the gbrain runtime blocks a reply if the skill
never loads.
The moment of evaluation is delivery, not request. The gate evaluates when substantial analysis (>=500 words of structured output on a user-shared document) is ABOUT to be delivered — the analysis is done and the reply is being composed. At that moment, file the brain page FIRST, then deliver the analysis plus the page link in that same reply. The user should never have to ask "did you file this?"
What ships with it
1 file 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.
- 6d ago First seen · 531 lines · 182 tokens per session scan A d58464cd02a6
eiirp is a skill published in the GitHub repository garrytan/gbrain (29,591 stars, last pushed 2d ago), licensed MIT. It adds 182 tokens to every session and 5,169 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 2026-08-30.
Other skills, from other repositories
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
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…
Migrate
Intakes external content, classifies chunks against LifeOS taxonomy, commits with provenance. Sources: .md/.txt, stdin, LifeOS dirs, CLAUDE.md/Cursor/OpenAI Custom Instructions, Obsidian/Notion/Apple Notes exports. MigrateScan classifies → routing table. MigrateApprove with…
release
Cut a versioned release and publish everos to PyPI via the tag-triggered workflow.
personal-assistant
A personalized assistant that remembers your preferences.
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…