Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/sagargupta16/selfhub/claude-md)<a href="https://agentmods.dev/instructions/sagargupta16/selfhub/claude-md"><img src="https://agentmods.dev/badge/instructions/sagargupta16/selfhub/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 5.1 | $0.00862 | $0.00862 |
| Opus 5 | $0.00431 | $0.00431 |
| Sonnet 5 | $0.00172 | $0.00172 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
SelfHub CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Server speaks MCP over **stdio** -- you cannot poke it with curl or run it interactively. Verify via an MCP client, or check the startup log line (`Connected to MongoDB`, 9 tools listed). How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file stacks on top of the workspace root at
C:\Code\GitHub\:
- Root
CLAUDE.md-- voice, rules, routing map, references, skills, slash commands, conventions.- Root
MEMORY.md-- live facts across repos.- Root
STATUS.md-- live PR/CI/security dashboard..claude/resources/-- deep reference for collaboration, workflow, git, OSS, debugging, voice.Read those first. The guidance below only adds repo-specific context -- it does not override anything in the root.
Project
SelfHub is a personal MCP (Model Context Protocol) server -- a cross-assistant memory hub that stores notes, preferences, snippets, and tasks in MongoDB and exposes them as 9 MCP tools to any MCP client (Claude Desktop, VS Code Copilot).
Public repo at github.com/Sagargupta16/SelfHub. Runs locally as a stdio process launched by the client; nothing is deployed.
Stack
- Language: TypeScript 5, ESM
- Framework:
@modelcontextprotocol/sdk(stdio transport) - Database: MongoDB via Mongoose 9
- Package manager: pnpm
- Deploy target: local-only
Run
pnpm install
pnpm dev # tsx watch src/index.ts (auto-reload)
pnpm build # tsc -> build/
pnpm seed # load 6 sample memories + 2 contexts
Test
No test suite. pnpm typecheck (tsc --noEmit) is the only check. No CI workflows either -- .github/ holds only CODEOWNERS and FUNDING.yml; Renovate handles deps.
Entry points
src/index.ts-- the MCP server: all 9 tool definitions and request handlerssrc/seed.ts-- sample data seeder (pnpm seed)
Key files
src/services/memory.service.ts,src/services/context.service.ts-- business logicsrc/storage/mongodb-storage.ts-- persistence layersrc/db/schemas.ts+src/db/connection.ts-- Mongoose schemas and connectionsrc/models/-- TypeScript interfaces (memory, context)
Gotchas
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 · 72 lines · 862 tokens per session scan A c0fa3be5c033
SelfHub CLAUDE.md is an instructions file published in the GitHub repository Sagargupta16/SelfHub (5 stars, last pushed 2d ago), licensed MIT. It adds 862 tokens to every session, about $0.0043 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
repo-context-mcp AGENTS.md
Instructions for nduc99911/repo-context-mcp, covering agents.md — repo-context-mcp, project, layout, commands and conventions.
now-sdk-ext-mcp CLAUDE.md
Instructions for sonisoft-cnanda/now-sdk-ext-mcp, covering now-sdk-ext-mcp, project overview, architecture, directory structure and sibling projects.
second-brain AGENTS.md
AGENTS.md instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.
swag-mcp CLAUDE.md
Claude Code instructions for jmagar/swag-mcp, covering swag mcp - claude memory reference, project overview, core architecture, key components and common development commands.
agent-knowledge-cards AGENTS.md
AGENTS.md instructions for manojbajaj95/agent-knowledge-cards, covering agents.md, layout, on-disk cards, commands and rules.
state-memory-mcp copilot-instructions.md
Instructions for putervision/state-memory-mcp, covering state memory (state-memory-mcp), 1. priority order, 2. when to write to the graph, 3. workflow pattern and 4. codebase seeding on initialization.