honcho-memory

A set of instructions that enables Honcho, a service for remembering information across coding sessions, and tells the agent how to use that memory. It also describes how to search and save information when needed.

In plain words
What is it for?
Use it to recall earlier conversations, save important conclusions, check known user preferences, and provide richer context to other agents.
Why use it?
Without persistent memory, an agent may forget preferences, decisions, and previous work between sessions. This helps keep that context available.

Cursor rule

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 rules/plastic-labs/cursor-honcho/honcho-memory
Clone the repo
git clone --depth 1 https://github.com/plastic-labs/cursor-honcho
Per session 374 This file is loaded in full into every session.
When invoked 374 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 $0.00374 $0.00374
Opus 5 $0.00187 $0.00187
Sonnet 5 $0.00075 $0.00075
Haiku 4.5 $0.00037 $0.00037

Measured 2d ago against content hash 6680caed1668, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

honcho-memory 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.

plugins/honcho/rules/honcho-memory.mdc · 32 lines

What it actually says

Honcho Memory

You have persistent memory via Honcho. Context about the user, their preferences, and past work is loaded automatically at the start of every session.

How to use it:

  • Trust the Honcho context injected at session start. It contains what you know about the user - act on it.
  • Use chat or search MCP tools mid-conversation when you need context beyond what was loaded at startup.
  • Use create_conclusion to save new insights as you learn them: preferences, decisions, patterns, things the user has asked you not to do.
  • The user should never have to repeat themselves. If you've learned something before, you should already know it.
  • When delegating to subagents, the memory-analyst agent can perform deep memory queries for you.

Memory-aware behaviors:

  • Before asking the user a preference question, check if you already know the answer from loaded context.
  • When you discover a new user preference or pattern, save it with create_conclusion.
  • Reference past work naturally ("Last time we worked on X, you preferred Y...").
  • If context seems stale or you need deeper history, use the search tool.

If Honcho is not configured

If the session start context says Honcho is not configured, or if MCP tool calls return setup instructions instead of results:

  • Suggest running /honcho:setup for guided first-time configuration.
  • The user needs a free API key from https://app.honcho.dev and must set HONCHO_API_KEY in their shell config.
  • Do not repeatedly attempt MCP tool calls that will fail -- help the user get set up first.
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 · 32 lines · 374 tokens per session scan A 6680caed1668

Subscribe to this mod's changes

honcho-memory is a cursor rule published in the GitHub repository plastic-labs/cursor-honcho (6 stars, last pushed 6mo ago), licensed MIT. It adds 374 tokens to every session, about $0.0019 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 2026-08-31.