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.
git clone --depth 1 https://github.com/plastic-labs/cursor-honchoWrote 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/rules/plastic-labs/cursor-honcho/honcho-memory)<a href="https://agentmods.dev/rules/plastic-labs/cursor-honcho/honcho-memory"><img src="https://agentmods.dev/badge/rules/plastic-labs/cursor-honcho/honcho-memory/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.
<a href="https://agentmods.dev/rules/plastic-labs/cursor-honcho/honcho-memory"><img src="https://agentmods.dev/badge/rules/plastic-labs/cursor-honcho/honcho-memory.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00374 | $0.00374 |
| Opus 5.5 | $0.00150 | $0.00150 |
| Sonnet 5.5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00037 | $0.00037 |
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 2mo 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.
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
chatorsearchMCP tools mid-conversation when you need context beyond what was loaded at startup. - Use
create_conclusionto 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:setupfor guided first-time configuration. - The user needs a free API key from https://app.honcho.dev and must set
HONCHO_API_KEYin their shell config. - Do not repeatedly attempt MCP tool calls that will fail -- help the user get set up first.
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.
- 2mo ago First seen · 32 lines · 374 tokens per session scan A 6680caed1668
honcho-memory is a cursor rule published in the GitHub repository plastic-labs/cursor-honcho (7 stars, last pushed 11d ago), licensed MIT. It adds 374 tokens to every session, about $0.0015 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 2026-08-31.
Other cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Search dreamd at the start of a task and quote a hit. Append when the user corrects you or states a decision.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.
memsprout
Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.