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 instructions/hassancs91/brainoutside/claude-mdgit clone --depth 1 https://github.com/hassancs91/brainoutsideWrote 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/instructions/hassancs91/brainoutside/claude-md)<a href="https://agentmods.dev/instructions/hassancs91/brainoutside/claude-md"><img src="https://agentmods.dev/badge/instructions/hassancs91/brainoutside/claude-md.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 | $0.01796 | $0.01796 |
| Opus 5 | $0.00898 | $0.00898 |
| Sonnet 5 | $0.00359 | $0.00359 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
brainoutside CLAUDE.md 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 5d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BrainOutside — working notes for agents
Self-hosted memory server. A git repo of markdown is the user's brain; this Django app indexes it, serves it over REST + MCP with visibility tiers enforced server-side, and gates every write behind human approval.
Single-user, single-brain. That is the product, not a limitation.
Full architecture and milestones: docs/PLAN.md. Deploying:
docs/DEPLOY.md. (Internal working docs — launch plan, release
checklist, design docs — live untracked under docs/, maintainer's
machine only; see .gitignore.)
This repo is NOT the brain. The brain is a separate repo the server
clones into data/brain-repo. Never edit brain content from here.
Stack
Django 5.2 / Python 3.13, Postgres, Redis, Django-Q2. Docker Compose:
web + mcp + worker + postgres + redis.
| Path | What |
|---|---|
apps/mind/ |
The public read API — endpoints, tier enforcement, file serving, throttling |
apps/brain/ |
Entity index, git clone/sync, snapshots, graph |
apps/feeds/ |
Proposal → approval queue → signed commit |
apps/reader/ |
Reader agent, chat, SDK runner |
apps/brainconfig/ |
Ops UI, settings, /setup wizard, health |
apps/events/ |
Event log, SDK ledger, tasks |
apps/mcp_proxy/, apps/api_keys/ |
MCP transport, consumer keys + tiers |
apps/docs/ |
Self-documenting API reference at /docs/ |
templates/ops/, templates/setup/ |
The UI that matters |
assets/css/app.css |
Tailwind SOURCE (not served) |
static/css/tw.css |
Compiled artifact (committed, served) |
Settings: base → dev (DEBUG, SQLite) → docker (local full stack) →
prod. Containers run config.settings.docker locally,
config.settings.prod deployed.
Running it
.\dev.ps1 up | reload [svc] | logs [svc] | status | manage <cmd> | css [-Watch]
webself-reloads on Python edits.mcpandworkerneedreload.- Template edits need
reload web. - The clone at
data/brain-repohas no git credentials in-container: pull on the host, then.\dev.ps1 manage sync_brain --no-pull.
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.
- 5d ago First seen · 148 lines · 1,796 tokens per session scan A 51b1e41578bc
brainoutside CLAUDE.md is an instructions file published in the GitHub repository hassancs91/brainoutside (73 stars, last pushed 17d ago), licensed MIT. It adds 1,796 tokens to every session, about $0.0090 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 instructions, from other repositories
django-ai-boost AGENTS.md
AGENTS.md instructions for vintasoftware/django-ai-boost, covering agents.md, 1) project snapshot, 2) environment setup, 3) build / lint / format commands and 4) test commands.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Claude Code instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
flyto-core CLAUDE.md
Claude Code instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.