Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/rules/markmhendrickson/neotoma/cursor_rules_sync)<a href="https://agentmods.dev/rules/markmhendrickson/neotoma/cursor_rules_sync"><img src="https://agentmods.dev/badge/rules/markmhendrickson/neotoma/cursor_rules_sync.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 5.1 | $0.00038 | $0.00788 |
| Opus 5 | $0.00019 | $0.00394 |
| Sonnet 5 | $0.00008 | $0.00158 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
cursor_rules_sync 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ DO NOT EDIT THIS FILE DIRECTLY
This is a copy of: foundation/agent_instructions/cursor_rules/cursor_rules_sync.mdc
Source of truth: foundation/agent_instructions/cursor_rules/cursor_rules_sync.mdc
To edit this rule:
1. Edit the source file: foundation/agent_instructions/cursor_rules/cursor_rules_sync.mdc
2. Run '/setup_cursor_copies' to sync changes
This file will be overwritten when running setup_cursor_copies.
Cursor Rules Sync Rule
Ensures .cursor/rules/ and .cursor/commands/ remain synchronized with their source files in docs/ or foundation/agent_instructions/.
Implementation
Automated: Rule and command syncing is enforced by a pre-commit hook that runs when source files change.
Hook: scripts/linters/cursor_rules_sync_pre_commit.sh (configured in .pre-commit-config.yaml as cursor-rules-sync)
How it works:
- When files matching
docs/**/*.mdcorfoundation/agent_instructions/cursor_rules/**/*.mdcorfoundation/agent_instructions/cursor_commands/**/*.mdare staged, the hook runs automatically - Script executes
foundation/scripts/setup_cursor_copies.sh(or repo equivalent) - Updated
.cursor/rules/and.cursor/commands/files are staged automatically - Commit proceeds with synced files
Manual execution:
# Run the setup script directly
./foundation/scripts/setup_cursor_copies.sh
# Or via command
/setup_cursor_copies
/sync_cursor_files copies
Agent Actions
Agents do NOT need to manually run /setup_cursor_copies after editing rule sources — the pre-commit hook handles this automatically.
When creating or modifying rule/command sources:
- Edit source files only — in
docs/orfoundation/agent_instructions/, never.cursor/ - Commit changes — pre-commit hook will sync
.cursor/automatically - If editing outside of a commit (rare), run the setup script manually
Source File Locations
Foundation rules and commands:
- Source:
foundation/agent_instructions/cursor_rules/*.mdc,foundation/agent_instructions/cursor_commands/*.md - Copies:
.cursor/rules/,.cursor/commands/(synced via setup script)
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.
- 2d ago First seen · 75 lines · 38 tokens per session scan A ff1eba639af5
cursor_rules_sync is a cursor rule published in the GitHub repository markmhendrickson/neotoma (31 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 788 once invoked, about $0.0002 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 2026-09-03.
Other cursor rules, from other repositories
git-conventions
Git commit message conventions and PR merge strategy for jentic-one.
atomicmemory
AtomicMemory persistent memory protocol and MCP tool usage.
cairn-commit-network
Commits that run cairn hooks need unsandboxed network.
git-conventions
Apply when committing, branching, or opening a pull request. Conventional commit format, branch naming, PR scope.
gctrl
GCTRL long-term memory over MCP. Apply before answering any factual question about the user's organization, projects, people, systems, decisions, history, or file locations (unfamiliar proper nouns, "our/we" references, "what do we know about X"), and after substantive work to write conclusions back.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.