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/docs-plus/docs.plusWrote 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/docs-plus/docs.plus/agent-rules-and-memory)<a href="https://agentmods.dev/rules/docs-plus/docs.plus/agent-rules-and-memory"><img src="https://agentmods.dev/badge/rules/docs-plus/docs.plus/agent-rules-and-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/docs-plus/docs.plus/agent-rules-and-memory"><img src="https://agentmods.dev/badge/rules/docs-plus/docs.plus/agent-rules-and-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 | $0.01201 | $0.01201 |
| Opus 5.5 | $0.00480 | $0.00480 |
| Sonnet 5.5 | $0.00240 | $0.00240 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
agent-rules-and-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 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent rules and memory
Cursor does not read CLAUDE.md files. Claude Code does, and this repo files most of its rules
there, so Cursor needs this pointer to reach the same rules. Read in this order.
1. Durable memory
.agents/memory/ is a symlink to the Claude Code memory store, so both tools share one copy. Start
at .agents/memory/MEMORY.md — a one-line index of every memory file — then open the entries
relevant to the task.
It is gitignored and must stay that way. It records production hosts, project refs and infra details that must not reach a public repo.
2. Repo-wide rules
AGENTS.md at the repo root. Package manager, git and commit policy, code
quality, test policy, release safety, monorepo toolchain. Read it in full before any substantive
work.
3. Root CLAUDE.md
CLAUDE.md at the repo root. Claude Code loads it automatically at session
start; Cursor does not, so read it here. It indexes the per-directory CLAUDE.md files and carries
the ### Settled — do not re-propose list — decisions made, tried, and in most cases reverted
(including the TOC channel-map rework). That list exists in no other file; skipping this step risks
re-proposing a change the maintainer already rejected.
4. Directory-scoped rules
Rules for one area live in that area's CLAUDE.md. Claude Code loads these automatically by path;
in Cursor you must open them yourself. AGENTS.md §Filed by directory lists every section and its
file. The map:
| Working on | Read |
|---|---|
| Webapp UI, document features | apps/webapp/CLAUDE.md |
| Editor, TipTap, ProseMirror | apps/webapp/src/components/TipTap/CLAUDE.md |
| Chatroom, messaging, composer | apps/webapp/src/components/chatroom/CLAUDE.md |
| Hocuspocus, REST, persistence, production | apps/hocuspocus.server/CLAUDE.md |
| Admin dashboard | apps/admin-dashboard/CLAUDE.md |
| Supabase, SQL, RLS, storage | packages/supabase/CLAUDE.md |
| Extensions | extensions/CLAUDE.md |
| Cutting a product release | .cursor/skills/release-product/SKILL.md |
| Publishing a release | .cursor/skills/release-extensions/SKILL.md |
| Writing a README, CHANGELOG, report, runbook or PR description | .cursor/skills/tech-writer/SKILL.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 Changed · +1 lines · +21 tokens per session 472802bdada6
- 10d ago Changed · +7 lines · +96 tokens per session ee891f960487
- 24d ago Changed · +8 lines · +107 tokens per session 58ed96f66be3
- 1mo ago First seen · 81 lines · 977 tokens per session scan A eb9df91d1dc7
agent-rules-and-memory is a cursor rule published in the GitHub repository docs-plus/docs.plus (95 stars, last pushed yesterday), licensed MIT. It adds 1,201 tokens to every session, about $0.0048 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 2026-08-30.
Other cursor rules, from other repositories
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
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.
byterover-rules
ByteRover MCP Custom Instructions.
business-memory-bank
AI Agent Memory Management Rules (Business Context).
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.