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.
git clone --depth 1 https://github.com/Ertinox7711/SGRR-AGI-V2Wrote 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/commands/ertinox7711/sgrr-agi-v2/brain)<a href="https://agentmods.dev/commands/ertinox7711/sgrr-agi-v2/brain"><img src="https://agentmods.dev/badge/commands/ertinox7711/sgrr-agi-v2/brain/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/commands/ertinox7711/sgrr-agi-v2/brain"><img src="https://agentmods.dev/badge/commands/ertinox7711/sgrr-agi-v2/brain.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 | $0.00047 | $0.00508 |
| Opus 5.5 | $0.00019 | $0.00203 |
| Sonnet 5.5 | $0.00009 | $0.00102 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
brain 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.
What it actually says
brain-rag est le RAG maison : environ 66 000 extraits couvrant le brain de
Hermes (notes, dossiers, reels archives, journal), les skills Hermes, les skills
Claude Code, le CLAUDE.md global, PITFALLS.md, shops-registry.md et les
memoires des deux agents. Il rend des passages avec fichier:ligne.
Recherche demandee : $ARGUMENTS
Marche a suivre
- Lance la recherche :
wsl -u YOU -- bash -lic 'brain-rag "<la question>"'- hybride BM25 + bge-m3 par defaut, environ 2 s
--fast= BM25 seul ·--scope brain|hermes|claude|memory·-k N·--full- l'index se rafraichit tout seul (au plus une fois toutes les 10 min) ;
--refreshforce le controle,--indexreconstruit tout (30 s)
- Si la premiere formulation ne rend rien, reformule avec les mots du document (« no-verify », « 403 Cloudflare », « keep_alive ») plutot qu'avec les tiens. C'est ce qui fait la difference entre trouver et ne pas trouver.
brain-ragretrouve des passages, il ne raisonne pas : ouvre le fichier cite avant d'agir dessus. Un extrait indexe reflete l'etat au moment de l'indexation, pas forcement le disque d'aujourd'hui.- Reponds avec la reponse d'abord, puis les sources en
fichier:ligne.
Si vraiment rien ne sort apres deux formulations differentes, dis-le franchement et propose la source suivante (le fichier a lire, ou la question precise a poser a the operator) — n'invente pas.
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 · 33 lines · 47 tokens per session scan A 2a6811f9c8e7
brain is a command published in the GitHub repository Ertinox7711/SGRR-AGI-V2 (1 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 508 once invoked, about $0.0002 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 2026-09-09.
Other commands, from other repositories
querying
Query documents from a search index using type-safe filters with support for pagination, sorting, field selection, scoring, and highlighting. Count matching documents efficiently without returning results.
agent
Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.
ingest
Manually add knowledge to the Weaviate store.
inference.embed
Embed one or more texts into vectors.
proofrag
Evaluate a RAG/LLM app — generate a golden set, judge it, and produce a scorecard.
vector.batch_upsert
Upsert multiple vectors in one itemwise batch.