dreamd-recall

dreamd-recall is a cursor rule for Cursor from botzrDev/dreamd. It costs 54 tokens per session (450 once invoked), scanned A, original, Apache-2.0.

A set of rules for recalling lessons, decisions, and earlier project context from a memory service called dreamd.

In plain words
What is it for?
Use it when starting work in an existing project, revisiting a past decision, checking documented preferences, or recording a useful new lesson.
Why use it?
It reduces repeated mistakes and helps an agent follow decisions that were already documented in the project.

Cursor rule for Cursor

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/botzrdev/dreamd/dreamd-recall
Clone the repo
git clone --depth 1 https://github.com/botzrDev/dreamd

Made for: Cursor.

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 dreamd-recall

README.md
[![agentmods](https://agentmods.dev/badge/rules/botzrdev/dreamd/dreamd-recall.svg)](https://agentmods.dev/rules/botzrdev/dreamd/dreamd-recall)
Your own site
<a href="https://agentmods.dev/rules/botzrdev/dreamd/dreamd-recall"><img src="https://agentmods.dev/badge/rules/botzrdev/dreamd/dreamd-recall.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 450 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00054 $0.00450
Opus 5 $0.00027 $0.00225
Sonnet 5 $0.00011 $0.00090
Haiku 4.5 $0.00005 $0.00045

Measured 3d ago against content hash 3960451bd873, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dreamd-recall scanned grade A 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl --unix-socket ~/.agent/dreamd.sock \
adapters/cursor/.cursor/rules/dreamd-recall.mdc · 36 lines

What it actually says

When to use

Use search_nodes (MCP) when:

  • Starting a new task in a project you have worked in before
  • The user references a past decision or problem
  • You are about to make a choice that has a documented prior

How to log a learning

When you discover something worth remembering, call append_node with:

  • skill_action: :: -separated key — always language-first, e.g. rust::error_handling, rust::api_design, rust::clippy::<lint_name>
  • source_harness: "cursor" (required — omitting causes a deserialization error)
  • pain: 0–10 (friction caused)
  • importance: 0–10 (how often this pattern recurs)
  • content: one clear sentence of what was learned
  • client_dedup_key (optional): first 60 chars of content, lowercased, spaces → underscores

Session activation

At session start, call search_nodes with the current task description as the query (preferred — works with or without the daemon).

If the daemon is running and you need user preferences from personal/, you may call GET /api/v1/preferences over the Unix socket with the required X-Agent-Root header:

curl --unix-socket ~/.agent/dreamd.sock \
  -H "X-Agent-Root: /absolute/path/to/your-project" \
  http://localhost/api/v1/preferences

Read the body field. If non-empty, use it to calibrate pain and importance values. If the daemon is not running, skip silently.

MCP protocol note

After initialize, send notifications/initialized before calling any tools. Without it, search_nodes returns empty results silently.

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. 3d ago First seen · 36 lines · 54 tokens per session scan A 3960451bd873

Subscribe to this mod's changes

dreamd-recall is a cursor rule published in the GitHub repository botzrDev/dreamd (3 stars, last pushed 5d ago), licensed Apache-2.0. It adds 54 tokens to every session and 450 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.