GoodMemory CLAUDE.md

GoodMemory CLAUDE.md is an instructions file for coding agents from hjqcan/GoodMemory. It costs 301 tokens per session, scanned A, original, MIT.

A repository instruction file for using GoodMemory, a system that stores and retrieves durable project facts and decisions for Claude Code.

In plain words
What is it for?
It guides memory retrieval, searching, tracing, and saving of project facts, decisions, preferences, and blockers.
Why use it?
It helps the agent recover important context across prompts and avoid re-deriving or overwriting known project information.

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/hjqcan/goodmemory/claude-md
Clone the repo
git clone --depth 1 https://github.com/hjqcan/GoodMemory

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 GoodMemory CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hjqcan/goodmemory/claude-md.svg)](https://agentmods.dev/instructions/hjqcan/goodmemory/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hjqcan/goodmemory/claude-md"><img src="https://agentmods.dev/badge/instructions/hjqcan/goodmemory/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 301 This file is loaded in full into every session.
When invoked 301 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 $0.00301 $0.00301
Opus 5 $0.00151 $0.00151
Sonnet 5 $0.00060 $0.00060
Haiku 4.5 $0.00030 $0.00030

Measured yesterday against content hash e79d101e7e67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

GoodMemory 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 yesterday.

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 · 15 lines

What it actually says

GoodMemory Claude Code

This repository uses GoodMemory (installed Claude Code host path) for durable, governed memory.

Memory protocol:

  • Hook-injected "Developer memory notes" blocks are memory retrieved for the current prompt. Read them before planning and prefer them over re-deriving project facts; verify time-sensitive facts against the repo before acting on them.
  • When injected context is missing or insufficient, call goodmemory_get_context with a specific question (any question, not just the current prompt).
  • When you need specific records rather than a rendered summary, call goodmemory_search_index and then goodmemory_get_records. When a memory looks wrong or is unexpectedly missing, call goodmemory_trace_recall to see why it was or was not selected.
  • When you learn a durable fact, decision, preference, or blocker worth keeping and the goodmemory_remember tool is available, persist it with one clear statement per call. Writes are governed and auditable; the result explains any rejection.
  • Treat exported artifact files as projections, not canonical truth, and do not restate injected memory verbatim into files or commit messages.

GoodMemory complements Claude Code auto-memory: keep your own session working notes in MEMORY.md; keep durable project facts, decisions, and preferences in GoodMemory so they surface per-prompt with provenance. Do not copy hook-injected GoodMemory content into MEMORY.md.

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. yesterday First seen · 15 lines · 301 tokens per session scan A e79d101e7e67

Subscribe to this mod's changes

GoodMemory CLAUDE.md is an instructions file published in the GitHub repository hjqcan/GoodMemory (17 stars, last pushed 2d ago), licensed MIT. It adds 301 tokens to every session, about $0.0015 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 2026-09-04.