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.
npx agentmods add instructions/hjqcan/goodmemory/claude-mdgit clone --depth 1 https://github.com/hjqcan/GoodMemoryWrote 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.
[](https://agentmods.dev/instructions/hjqcan/goodmemory/claude-md)<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- yesterday First seen · 15 lines · 301 tokens per session scan A e79d101e7e67
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.
Other instructions, from other repositories
infinity-context AGENTS.md
AGENTS.md instructions for 777genius/infinity-context, covering agents.md, project intent, source of truth and implementation rule.
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.
mnemic CLAUDE.md
Claude Code instructions for dongtang3/mnemic: This project includes a project-level .mcp.json for the Mnemic memory MCP server.
mcp-light-memory AGENTS.md
AGENTS.md instructions for PeterPirog/mcp-light-memory, covering agent operating contract and persistent agent memory: mcp light memory (internalrag).
mnemic AGENTS.md
AGENTS.md instructions for dongtang3/mnemic: Mnemic is a graph-backed long-term memory substrate for coding agents and LLM applications.
lerim CLAUDE.md
Claude Code instructions for nablo-io/lerim, a project described as: Compiles AI agent traces and truns them into reusable context.