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/open-latch/latchWrote 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/open-latch/latch/cursor_rule_snippet)<a href="https://agentmods.dev/rules/open-latch/latch/cursor_rule_snippet"><img src="https://agentmods.dev/badge/rules/open-latch/latch/cursor_rule_snippet/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/open-latch/latch/cursor_rule_snippet"><img src="https://agentmods.dev/badge/rules/open-latch/latch/cursor_rule_snippet.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 | $0.00555 | $0.00555 |
| Opus 5.5 | $0.00222 | $0.00222 |
| Sonnet 5.5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
cursor_rule_snippet 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 1mo 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
latch Cursor activation
This rule is managed by Latch. Re-run {{KB_HOME}}/bin/install_cursor.sh --yes
from this project to refresh it.
Treat AGENTS.md as the shared Latch contract for live reads, authority and
reconciliation, visible receipts, durable capture, write hints, and compaction.
This rule adds Cursor-specific enforcement:
- If the IDE has no Latch tools, do not repeatedly call
latch_gate. Ask the user to open Cursor Settings > Tools & MCP, enable workspace serverlatch, confirm it reports tools enabled (count may vary), and start a fresh Agent chat.agent mcp listdoes not prove the IDE toggle. - Before an implementation mutation, call
latch_gateonce with this prompt verbatim. Whenfindings.must_display_to_user=true, show the Latch gate block before editing. - If the gate is skipped, degraded, has no recommendation, or used a rephrased request, say so and do not mutate while the opt-in gate hook is active.
- If
preToolUsedenies a mutation for a missing current-prompt receipt, runlatch_gateon the current request, surface the findings, and retry. Never work around or disable the hook silently. - Explicit Latch slash workflows use a separate one-shot operation receipt bound to the Cursor session, prompt, expected tool, and exact arguments. A general gate receipt cannot override that narrow lane.
- Preview does not authorize apply. Only a matching successful
postToolUseresult advances preview state./latch-pmmust display the read-onlylatch_pm_previewresult and digest-bind the exact staging decision before one matchinglatch_insert. - Free-form Shell commands are mutation-capable. Before the gate, use Cursor's exact native read tools rather than inferring safety from a program name.
- Use
/latch-seedonly for the exact current hook-provided Cursor transcript; preview candidates before any confirmed staging write.
Cursor's installed surface is project MCP, this rule, shared AGENTS.md,
.cursor/commands, and .cursor/skills. --with-hooks adds session, gate,
and activity hooks. The Cursor Agent CLI is the native model backend.
Manual compaction is fail-closed on the exact current
transcript_path; Latch never discovers or guesses historical Cursor
transcripts.
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.
- 1mo ago First seen · 47 lines · 555 tokens per session scan A 7868e222cda0
cursor_rule_snippet is a cursor rule published in the GitHub repository open-latch/latch (9 stars, last pushed 5d ago), licensed Apache-2.0. It adds 555 tokens to every session, about $0.0022 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
handoff
Export a Waybill Bundle by default, or import one when explicitly requested.
waybill
Alias for the Waybill handoff workflow.
agent-workspace
Repository evidence and validated engineering workflows.
tech-stack
Cursor rule "tech-stack" from yu-iskw/coding-agent-fabric, covering tech stack, pnpm workspace & monorepo best practices, common commands, workspace protocol and dependency management.
using-specgate
Route explicit SpecGate work.
frontend
UI/component conventions. Apply when building or changing user-facing frontend code.