synaptra: Instructions file for Claude Code

CLAUDE.md

synaptra CLAUDE.md is an instructions file for Claude Code from kaushikhazra/synaptra. It costs 2,145 tokens per session, scanned A, original, MIT.

A repository-specific instruction guide for Synaptra, a public Python package that provides memory storage for software agents. It explains the project's architecture, branding rules, and relationship to a private upstream project.

In plain words
What is it for?
Use it when modifying Synaptra code, architecture, branding, or release-related files. It is also relevant when deciding where a change must be made first.
Why use it?
It helps an agent make changes that match the project's design and public-release constraints. It reduces the risk of adding behavior here that does not exist in the upstream source.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is kaushikhazra/synaptra's own configuration. It tells Claude Code how to work on synaptra itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything synaptra configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kaushikhazra/synaptra. 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/kaushikhazra/synaptra/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kaushikhazra/synaptra

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.

agentmods badge for synaptra CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kaushikhazra/synaptra/claude-md/github.svg)](https://agentmods.dev/instructions/kaushikhazra/synaptra/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kaushikhazra/synaptra/claude-md"><img src="https://agentmods.dev/badge/instructions/kaushikhazra/synaptra/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.

agentmods 80×15 button for synaptra CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kaushikhazra/synaptra/claude-md"><img src="https://agentmods.dev/badge/instructions/kaushikhazra/synaptra/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,145 This file is loaded in full into every session.
When invoked 2,145 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02145 $0.02145
Opus 5.5 $0.00858 $0.00858
Sonnet 5 $0.00429 $0.00429
Haiku 4.5 $0.00215 $0.00215

Measured 11d ago against content hash 6aae39066c64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-25, from the pricing page.

Security

Grade A, and why

synaptra 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 11d 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 · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Synaptra — Project Instructions

What This Is

Biologically-inspired agent memory, exposed as an MCP server over Streamable HTTP. Decay-aware storage with multi-strategy retrieval, automatic linking, contradiction detection, consolidation and version history.

This is a published PyPI package. pip install synaptra, currently 2.0.0, MIT. People outside this machine have it installed. Every change here is a public change.


⚠ THE ONE THING THAT MAKES THIS REPO DIFFERENT

Synaptra is the public mirror of a private upstream.

   C:/Projects/cognitive-memory     upstream · internal · where changes are made first
            │
            │  same change, while it is fresh
            ▼
   C:/Projects/synaptra             this repo · public · PyPI
            │
            ▼
   C:/Projects/second-brain         workspace template built on the synaptra substrate

⇒ Changes flow one way: cognitive-memory → synaptra. Do not invent behaviour here that upstream does not have. If something is wrong here and also wrong upstream, it gets fixed in both, in the same pass.

⭐ Why the coupling is strict: a port that happens with the change is a port. A port that happens later is a migration, and migrations are where the two copies quietly diverge. They have diverged once already.

Upstream is a plain git repo on this machine and you can read it directly. git -C C:/Projects/cognitive-memory log, show, diff. Read the real commit rather than asking for a summary of it.


⛔ THE BRANDING DELTA — NEVER PORT OVER THESE

Upstream and this repo are deliberately different in the following places. A file-level copy from cognitive-memory will destroy every one of them. Port the behaviour, re-apply the names.

cognitive-memory synaptra
package dir src/cognitive_memory/ src/synaptra/
imports cognitive_memory.x synaptra.x
dist name cognitive-memory synaptra
console scripts cognitive-memory, … synaptra, synaptra-service, synaptra-cli, plus a cm alias
MCP self-name — FastMCP("synaptra") in server.py
env prefix COGNITIVE_MEMORY_* SYNAPTRA_*
data dir ~/.cognitive-memory/ ~/.synaptra/

Read the full file on GitHub · 151 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. 11d ago First seen · 151 lines · 2,145 tokens per session scan A 6aae39066c64

Subscribe to this mod's changes

synaptra CLAUDE.md is an instructions file published in the GitHub repository kaushikhazra/synaptra (0 stars, last pushed 2d ago), licensed MIT. It adds 2,145 tokens to every session, about $0.0086 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 2026-09-14.

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 · 9,406 tokens

spec-kit AGENTS.md

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

github/spec-kit · 7,326 tokens

next.js AGENTS.md

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 · 6,985 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 · 5,153 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens