agentleFS
IgorGanapolskyIgorGanapolsky/mac-yolo-safeguards/.cursor/rules/decision-stack.mdc

mac-yolo-safeguards / rules

Cursor rule3 starsChanged 3 days agoMITView on GitHub

Always ground non-trivial decisions in DS, ML, and Agentic RAG before acting or claiming shipped

The file

We split this decision-stack.mdc into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before any non-trivial decision, root-cause call, or ship claim:

    line 10
  2. Distinctive:

    Never claim "synced", "fixed", or "shipped" without evidence + RAG check.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 6,809 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
decision-stack.mdc
---
description: Always ground non-trivial decisions in DS, ML, and Agentic RAG before acting or claiming shipped
alwaysApply: true
---

# Decision stack — DS / ML / Agentic RAG

**Always** ground decisions in Data Science, ML, and Agentic RAG — user directive.

Before any non-trivial decision, root-cause call, or ship claim:

0. **Orchestrator** — `node tools/agent-session-start.js` (LaunchAgent health + CEO brief; `--full` before ship claims)
1. **RAG** — `node tools/agent-decision-stack.js --task "<decision>" --json` (or `mcp__thumbgate__recall`)
2. **If MISTAKE lesson matches current plan** — change the plan before acting
3. **Telemetry** — structured metrics (CI run ids, test counts, gateway health, durations) not intuition
4. **Hermes operator ML** — `node tools/hermes-decision-loop.js --json` when Telegram/gateway is involved
5. **Revenue DS** — `node tools/pipeline-data-science.js` when prioritizing dollars
6. **Verify** — scoped proof commands in the same turn
7. **Capture** — `mcp__thumbgate__capture_memory_feedback` after fixes/incidents with concrete artifacts

Never claim "synced", "fixed", or "shipped" without evidence + RAG check. See [AGENTS.md](../../AGENTS.md) Decision stack section.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.