agentmods.dev

memoir: Instructions file for Claude Code

CLAUDE.md

memoir CLAUDE.md is an instructions file for Claude Code from zhangfengcdt/memoir. It costs 2,014 tokens per session, scanned C, original, Apache-2.0.

Project instructions for Memoir, a Git-like version-control system for AI memory. It stores structured memories, supports branches and merges, and serves coding agents through a command-line tool, an MCP server, and a Claude Code plugin.

In plain words
What is it for?
Working on memory storage, versioning, proofs, the command-line tool, the MCP server, or the Claude Code integration.
Why use it?
They provide the development commands, architecture overview, and strict rules about testing and committing changes.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is zhangfengcdt/memoir's own configuration. It tells Claude Code how to work on memoir 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 memoir configures →

not rated 624repo +3 changed 16d ago C scan 2,014 tokens original Apache-2.0
View source ↗ zhangfengcdt/memoir zhangfengcdt.github.io
Reuse

Borrowing it

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

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 memoir CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zhangfengcdt/memoir/claude-md"><img src="https://agentmods.dev/badge/instructions/zhangfengcdt/memoir/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,014 This file is loaded in full into every session.
When invoked 2,014 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.02014 $0.02014
Opus 5.5 $0.00806 $0.00806
Sonnet 5.5 $0.00403 $0.00403
Haiku 4.5 $0.00201 $0.00201

Measured 16d ago against content hash ecd03ae65e75, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

memoir CLAUDE.md scanned grade C with 1 finding 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 16d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Plugin works in non-git folders.** Single `main` memoir branch only; the Stop hook captures to `main`. `/memoir:onboard` switches to `project:onboard` (file-shape index built by deterministic stdlib extractors under
CLAUDE.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code working in this repository. Keep it terse — the full reference lives at https://zhangfengcdt.github.io/memoir/.

Project

Memoir is Git-like version control for AI memory, aimed at coding agents. A store is a Prolly-tree with semantic paths (workflow.coding.style, preferences.tools.memory), branch/commit/merge, and cryptographic proofs. Primary consumers: the memoir CLI, the MCP server, and the Claude Code plugin under plugins/claude-code/.

Development

Use the venv for everything:

source venv/bin/activate    # or `python -m venv venv && source venv/bin/activate`
make install-dev            # first time only

Before any commit, in order:

make format                 # black + isort + ruff --fix
make lint                   # must pass
make test                   # must pass

make ci runs the full pipeline (lint, test, security, docs). Use it before opening a PR.

Test a single file or case:

pytest tests/test_cli.py -v
pytest tests/ -k "test_function_name"

Critical rules

  • Never commit or push without explicit user permission. This includes auto-mode. Ask.
  • Never create test data directories inside the project. Use /tmp/ for anything transient.
  • Never print() for debugging. Use logging, or write to /tmp/.
  • Don't skip make lint / make test — CI will block the PR anyway, fix it locally.
  • Don't bypass the taxonomy. All memories go through semantic paths, never raw UUIDs.
  • type-check is non-blocking (237 pre-existing mypy errors, tracked as tech debt) — do not add new ones, but don't gate work on them.

Architecture at a glance

  • src/memoir/store/ — ProllyTree store, LangGraph BaseStore adapter, git-like versioning.
  • src/memoir/taxonomy/ — fixed (SemanticTaxonomy) and iterative (LLMIterativeTaxonomy) path systems, ~200 paths, 3 levels.
  • src/memoir/classifier/ — IntelligentClassifier (LLM + prompt caching) and SemanticClassifier (pattern, 1–5ms).
  • src/memoir/search/ — single-stage IntelligentSearchEngine, taxonomy cached into the system prompt.
  • src/memoir/core/ — ProllyTreeMemoryStoreManager (drop-in LangMem replacement), ProfileMemento, TimelineMemento.
  • src/memoir/services/ — StoreService, MemoryService, BranchService, CryptoService, SyncService (reusable business logic). SyncService is the memoir-cloud client: stores addressed as <owner>/<store>, git remote origin, chunks before refs, gated on MEMOIR_API_KEY.
  • src/memoir/cli/ — Click CLI (memoir entry point). Supports --json and the agent env vars MEMOIR_STORE, MEMOIR_JSON. Cloud verbs (remote, push, pull, fetch) live in cli/commands/sync.py; tests use the fake gateway in tests/fake_cloud.py (real git http-backend, no network).
  • src/memoir/ui/ — web UI (Python HTTP server + React/Vite SPA). Handlers under ui/handlers/, frontend source under ui/webapp/src/, built bundle at ui/webapp/dist/.
  • plugins/claude-code/ — Claude Code plugin: slash commands, skills, hooks, and a mod (hooks/mod/, Claude Code ≥ 2.1.287) for /memoir:pane + the hint-line status. When touching the mod run claude plugin validate plugins/claude-code and claude plugin test plugins/claude-code; $ never crosses a function boundary and $.state atoms stay in the hooks module (the validator reads both off the source).
  • tests/ — unit + integration + versioning + CLI tests. Run with pytest.

Read the full file on GitHub · 108 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. 16d ago Changed · +86 tokens per session ecd03ae65e75
  2. 23d ago Changed · +89 tokens per session ce001f59539b
  3. 1mo ago First seen · 108 lines · 1,839 tokens per session scan C 4c3de399f3bf

Subscribe to this mod's changes

memoir CLAUDE.md is an instructions file published in the GitHub repository zhangfengcdt/memoir (624 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,014 tokens to every session, about $0.0081 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Git and workflowMemory and context
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 · 9,715 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 · 7,786 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

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens