agentleFS
kryptophonikkryptophonik/SRE-Skills/.cursor/rules/sre-safety-gates.mdc

SRE-Skills / rules

Cursor rule4 starsChanged 23 days agoMITView on GitHub

SRE pack safety gates (always on)

The file

We split this sre-safety-gates.mdc into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Diagnose read-only first: Use only read commands and read-only MCP tools (get, describe, logs, history, plan, queries, dashboards).

    line 10
  2. Very specific:

    Act: Run exactly what was approved — nothing more.

    line 13
  3. Distinctive:

    Stop and escalate if worse: If metrics degrade, the action fails, or the outcome is unexpected: stop, do not try further fixes on your own, …

    line 15
  4. Very specific:

    Never run a write command, call an MCP write tool, or post an external message without explicit human approval.

    line 17

≈ “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
sre-safety-gates.mdc
---
description: SRE pack safety gates (always on)
alwaysApply: true
---

<!-- GENERATED by scripts/build-targets.py from .claude/skills/*/SKILL.md. Do not edit; edit the skills and re-run. -->

# SRE safety gates

1. **Diagnose read-only first.** Use only read commands and read-only MCP tools (`get`, `describe`, `logs`, `history`, `plan`, queries, dashboards). Change nothing.
2. **Propose with risk and reversibility.** For each action state: exact command/change, target (env, account/subscription/project, cluster, namespace, service), risk (low/med/high), reversible (yes/no), expected effect, rollback plan.
3. **Wait for explicit human approval.** Do not run any prod-changing command, call any MCP write tool, or send/post any external message (Slack, status page, email, PagerDuty/Opsgenie note) until a human explicitly approves that specific action. Silence, "looks fine", or approval of a different action is not approval.
4. **Act.** Run exactly what was approved — nothing more. Prefer dry-run/diff/plan output first.
5. **Verify.** Confirm error rate, latency and saturation are back to baseline / within SLO; watch 5–15 min.
6. **Stop and escalate if worse.** If metrics degrade, the action fails, or the outcome is unexpected: stop, do not try further fixes on your own, roll back if approved, and escalate to the Incident Commander / on-call.

Never run a write command, call an MCP write tool, or post an external message without explicit human approval. Skills live in `.claude/skills/` (Cursor reads them natively); manual-only skills must be started by the user with `/<skill-name>`.

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.