knowledge-graph CLAUDE.md

A persistent memory layer for Claude Code that records file operations, finds files that often change together, and creates distributed CLAUDE.md guidance files. It is built as shell scripts using jq and git.

In plain words
What is it for?
Use it to initialise project knowledge, update it after changes, check its status, query stored knowledge, and validate its shell scripts.
Why use it?
It helps an agent retain project knowledge and surface relationships between files without requiring external services or a separate dependency-heavy system.

Instructions file

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/hilyfux/knowledge-graph/claude-md
Clone the repo
git clone --depth 1 https://github.com/hilyfux/knowledge-graph
Per session 819 This file is loaded in full into every session.
When invoked 819 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 $0.00819 $0.00819
Opus 5 $0.00409 $0.00409
Sonnet 5 $0.00164 $0.00164
Haiku 4.5 $0.00082 $0.00082

Measured 2d ago against content hash 42ca70d57d1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-graph 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 2d 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 · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Project Is

Knowledge Graph is a persistent memory layer for Claude Code. It tracks file operations via hooks, mines co-change patterns with a pure bash+jq inference engine, and generates distributed CLAUDE.md knowledge nodes across target projects — all with zero external dependencies beyond jq and git.

Validation Commands

# Syntax check all scripts (required before any PR)
bash -n standalone/install.sh
bash -n standalone/skills/knowledge-graph/scripts/*.sh

# Optional deeper linting
shellcheck standalone/install.sh standalone/skills/knowledge-graph/scripts/*.sh

There is no test framework — validation is syntax checking and shellcheck.

Architecture

Pure bash project — no package.json, no build step, no transpilation.

Entry Points

  • standalone/install.sh — Installer: copies skill, merges hooks into target project's .claude/settings.json, migrates old data
  • standalone/skills/knowledge-graph/SKILL.md — Skill interface defining 4 modes: init, update, status, query

Runtime Scripts (standalone/skills/knowledge-graph/scripts/)

Script Purpose
track.sh Event recording + predictive module injection (called by hooks)
infer.sh Inference engine: cochange, sequences, decay, predict (pure jq)
analyze.sh Project scanning + pre-analysis
context.sh Context injection at startup/compact/subagent events
prompt-trigger.sh Detect completion/failure signals for auto-update
guard.sh Environment guard + shared helpers

Hook Wiring

Hooks are configured in .claude/settings.json and fire automatically:

  • PreToolUse(Read)track.sh read — records reads, predicts related modules
  • PostToolUse(Write/Edit)track.sh write — records changes, auto-triggers update every 15 writes
  • PostToolUseFailuretrack.sh failure — records errors for learning
  • SessionStartcontext.sh — injects active zones + pending events

Read the full file on GitHub · 82 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. 2d ago First seen · 82 lines · 819 tokens per session scan A 42ca70d57d1d

Subscribe to this mod's changes

knowledge-graph CLAUDE.md is an instructions file published in the GitHub repository hilyfux/knowledge-graph (17 stars, last pushed 2mo ago), licensed MIT. It adds 819 tokens to every session, about $0.0041 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens