What is shodh-memory CLAUDE.md?

Project instructions for Shodh-Memory, a Rust project that provides persistent memory through an MCP service. MCP is a standard way for AI agents to connect to external tools and data.

Use them when modifying Shodh-Memory, running checks or tests, creating worktrees, preparing commits, or working with its persistent-memory service.

They set safety and workflow rules, such as which Rust checks are allowed by default, how worktrees must be handled, and when external actions need approval.

How varun29ankuS/shodh-memory configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to varun29ankuS/shodh-memory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/varun29ankuS/shodh-memory/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/varun29ankuS/shodh-memory

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/varun29ankus/shodh-memory/claude-md/github.svg)](https://agentmods.dev/instructions/varun29ankus/shodh-memory/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/varun29ankus/shodh-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/varun29ankus/shodh-memory/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/varun29ankus/shodh-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/varun29ankus/shodh-memory/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 532 This file is loaded in full into every session.

When invoked 532 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00532	$0.00532
Opus 5.5	$0.00213	$0.00213
Sonnet 5.5	$0.00106	$0.00106
Haiku 4.5	$0.00053	$0.00053

Measured 2mo ago against content hash 8aa746bded0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

shodh-memory 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 2mo 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.

CLAUDE.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shodh-Memory Project Instructions

MUST Rules

MUST NOT run cargo build or cargo run unless the user explicitly asks. Only cargo check, cargo clippy, and cargo test are allowed by default.
MUST NOT add "Co-Authored-By" or "Generated with Claude Code" to commits. Clean commit messages only.
MUST NOT comment on GitHub issues/PRs without showing user a draft first.
MUST NOT create git worktrees outside the project folder. All worktrees go in <repo>/.claude/worktrees/<name>. Never C:/smt, never ~/.claude/worktrees, never a sibling directory. A worktree outside kalki-v2/ misses the parent .cargo/config.toml, builds to a different artifact path, and silently forks target/ into two complete trees.
MUST remove a worktree once its branch is merged or abandoned. Before removing one, run git status --porcelain in it and confirm any untracked files exist in git — untracked content is the only thing git worktree remove cannot recover, since branch refs survive removal.

Code Standards

IMPORTANT: Production grade code only. No TODOs, no placeholders, no mocks, no stubs.
IMPORTANT: Understand architecture and data flow before fixing anything. Read files before editing.
IMPORTANT: No assumptions. Always read the actual source code to verify API shapes, response fields, status codes, endpoint methods, and data structures before writing code or tests against them. Never guess.
All changes go through PR workflow: branch → commit → push → PR → merge.

Persistent Memory (shodh-memory MCP)

You have session continuity via shodh-memory hooks. Key behaviors:

Relevant memories surface automatically — don't manually "check" memory
Use remember sparingly (high-importance only), forget for corrections
Use list_todos at session start for pending work
The memory system you're using IS this codebase

Codebase Map

src/ — Rust core (memory, API server, embeddings, graph, vector search)
mcp-server/ — TypeScript MCP server (45 tools, index.ts)
tui/ — Rust TUI dashboard
hooks/ — Claude Code hooks for automatic memory
python/ — Python bindings (PyO3/maturin)
Architecture: RocksDB + Vamana/SPANN vector search + knowledge graph with Hebbian learning

Read the full file on GitHub · 31 lines

Changes

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.

2mo ago First seen · 31 lines · 532 tokens per session scan A 8aa746bded0d

Subscribe to this mod's changes

shodh-memory CLAUDE.md is an instructions file published in the GitHub repository varun29ankuS/shodh-memory (321 stars, last pushed 4d ago), licensed Apache-2.0. It adds 532 tokens to every session, about $0.0021 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.

Memory and context Rust ai-agents claude knowledge-graph local-first mcp

shodh-memory CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
shodh-memory CLAUDE.mdvarun29ankuS/shodh-memory	Instructions file	321	4d ago	Apache-2.0	A	532	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

shodh-memory: Instructions file for Claude Code