What is flux-memory CLAUDE.md?

Repository instructions for Flux Memory, a Python and SQLite system that stores connected pieces of information with source labels, clustering, decay, and administrative safeguards.

Use them when developing Flux Memory's storage, graph, propagation, clustering, feedback, health monitoring, or administrative controls.

They state design constraints that must be preserved when modifying the memory system.

How harsh5i/flux-memory configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to harsh5i/flux-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/harsh5i/flux-memory/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/harsh5i/flux-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/harsh5i/flux-memory/claude-md/github.svg)](https://agentmods.dev/instructions/harsh5i/flux-memory/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/harsh5i/flux-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/harsh5i/flux-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/harsh5i/flux-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/harsh5i/flux-memory/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 682 This file is loaded in full into every session.

When invoked 682 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	$0.00682	$0.00682
Opus 5.5	$0.00273	$0.00273
Sonnet 5.5	$0.00136	$0.00136
Haiku 4.5	$0.00068	$0.00068

Measured 2mo ago against content hash cee333707704, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

flux-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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flux Memory v0.5 — CLAUDE.md

Spec: docs/flux-memory-docs.md
Checkpoint log: keep local checkpoint files outside this repository.

Hard constraints (never deviate)

Python 3.10+, SQLite 3.35+ with WAL mode
networkx.community.louvain_communities for clustering — NOT python-louvain
Lazy decay only (effective_weight computed at read time from last_used)
MAX_EDGES_PER_GRAIN cap with weakest-edge eviction
Every grain has provenance: user_stated / ai_stated / ai_inferred / external_source
Admin channel gatekeeper protocol (§7.6): confirmation token, rate limiting, audit log, 24h purge undo window. Not exposed via MCP. (Password/TOTP gating removed by owner decision 2026-06-11 — confirmation token remains.)
Soft cluster membership with touch-weight accumulator and split/merge remapping (§13.2). NOT disjoint.
Multi-signal feedback with provenance multipliers (§7.1). NOT single boolean.
Health Monitor is first-class — build alongside the engine, not after.

Repo layout

src/flux/
  __init__.py       public API
  config.py         all parameters (Section 5)
  graph.py          data classes
  storage.py        SQLite access layer
  propagation.py    signal propagation + lazy decay
  reinforcement.py  reinforce + penalize + shortcuts
  decay.py          cleanup_pass + expiry_pass
  clustering.py     Louvain soft clustering
  promotion.py      grain promotion
  [health.py]       Health Monitor (Track 3)
  [extraction.py]   grain extractor LLM (Track 2)
  [retrieval.py]    high-level flux_retrieve surface (Track 4)
  [admin.py]        admin channel (Track 4)
tests/
  conftest.py
  test_config.py
  test_schema.py
  test_storage.py
  test_propagation.py
  test_reinforcement.py
  test_decay.py
  test_clustering.py
  test_promotion.py

Development rules

One algorithm at a time, with pytest tests before moving on.
Commit at each Track 1 step boundary with message: Track 1 step N: description (§X.Y)
Spec unclear? STOP and note the question. Do not silently improvise.
Internal helpers not in the spec: implement simplest version consistent with usage and note the choice.
Structured JSON logging (§11.5).
All parameters from config.py — none hardcoded.

Read the full file on GitHub · 57 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 · 57 lines · 682 tokens per session scan A cee333707704

Subscribe to this mod's changes

flux-memory CLAUDE.md is an instructions file published in the GitHub repository harsh5i/flux-memory (4 stars, last pushed 4mo ago), licensed MIT. It adds 682 tokens to every session, about $0.0027 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 2026-08-31.

Databases Memory and context ai-memory knowledge-graph llm-memory mcp-server rag-alternative

flux-memory CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
flux-memory CLAUDE.mdharsh5i/flux-memory	Instructions file	4	4mo ago	MIT	A	682	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	yesterday	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

flux-memory: Instructions file for Claude Code