agentmods.dev

flux-memory CLAUDE.md

flux-memory CLAUDE.md is an instructions file for coding agents from harsh5i/flux-memory. It costs 682 tokens per session, scanned A, original, MIT.

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

In plain words
What is it for?
Use them when developing Flux Memory's storage, graph, propagation, clustering, feedback, health monitoring, or administrative controls.
Why use it?
They state design constraints that must be preserved when modifying the memory system.

Instructions file

not rated 4 2mo ago A scan 682 tokens original MIT
View the source file harsh5i/flux-memory
Install

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.

agentmods
npx agentmods add instructions/harsh5i/flux-memory/claude-md
Clone the repo
git clone --depth 1 https://github.com/harsh5i/flux-memory

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.

agentmods badge for flux-memory CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/harsh5i/flux-memory/claude-md.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.svg" alt="Measured on agentmods" 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. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00682 $0.00682
Opus 5 $0.00341 $0.00341
Sonnet 5 $0.00136 $0.00136
Haiku 4.5 $0.00068 $0.00068

Measured 4d ago against content hash cee333707704, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

  1. 4d 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 2mo ago), licensed MIT. It adds 682 tokens to every session, about $0.0034 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 2026-08-31.

DatabasesMemory and contextai-memoryknowledge-graphllm-memorymcp-serverrag-alternative
Related

Other instructions, from other repositories

nobrainr CLAUDE.md

Claude Code instructions for vicquick/nobrainr, covering nobrainr — collective agent memory service, what this is, canonical categories, architecture and routing (when using a reverse proxy).

vicquick/nobrainr · 7,057 tokens

Muninn GEMINI.md

Gemini CLI instructions for wjohns989/Muninn, covering muninn mcp — sota+ development context, 🚀 sota+ development philosophy, 🛠 operational guidelines (always-on), 🏗 system architecture and 📂 project structure.

wjohns989/Muninn · 815 tokens

graph-memory CLAUDE.md

Instructions for stevepridemore/graph-memory, covering graph memory, when to consult the graph, how to use it, writing to the graph during conversation and when to write (call graphrelate).

stevepridemore/graph-memory · 632 tokens

automem CLAUDE.md

Instructions for verygoodplugins/automem, covering claude.md, project overview, development commands, setup environment and development.

verygoodplugins/automem · 4,543 tokens

remnic AGENTS.md

AGENTS.md instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.

joshuaswarren/remnic · 31,441 tokens

memora CLAUDE.md

Claude Code instructions for agentic-box/memora, covering memora and memory.

agentic-box/memora · 63 tokens