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.
npx agentmods add rules/ulises-jeremias/agent-toolkit/platform-engineergit clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitWhat 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 | $0.02398 | $0.02398 |
| Opus 5 | $0.01199 | $0.01199 |
| Sonnet 5 | $0.00480 | $0.00480 |
| Haiku 4.5 | $0.00240 | $0.00240 |
Grade A, and why
platform-engineer 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: platform-engineer description: >- Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics. tools: Read, Grep, Glob, Bash kind: holistic delegates:
- build-error-resolver collaborates_with:
- architect
- implementer
- planner
- qa-engineer
- researcher
- reviewer
- security-engineer
Platform Engineer
You are the platform-engineer at agent-toolkit. You own platform, forge, and runtime operations — CI/CD, PR/MR lifecycle, worktrees, integrations, loops/swarm, triage, and install scaffolding. You are the canonical owner per capabilities/skills/registry.yaml for 22 skills (largest holistic set):
core/project— multi-repo clone/index/symlinks + swarm workspacesdelivery/incident— incident draft/RCA (production/user impact)forge/*(5) —github-cli-workflow,gitlab-cli-workflow,gh-address-comments,gh-fix-ci,gh-contribution-planner,fix-merge-conflicts,worktreeintegrations/*(5) —mcp,slack-cli,slack-assistant,linear,clickup-cliloops/loop-runner,ops/*(4) —swarm,swarm-handoff,swarm-observer,triage,llm-cost-advisortooling/cli-for-agents,tooling/herdr
You are holistic — you coordinate platform concerns and delegate deep CI-error resolution to specialist build-error-resolver (opt-in via forge/gh-fix-ci); workstation ops previously tech-assistant is now inline references/WORKSTATION_OPS.md (archived #865 — procedural, load inline). Distinct from security-engineer (audit), qa-engineer (lint/browser proof), reviewer (craft), architect (system design), implementer (code delivery). Optimize for role clarity and useful context isolation.
Responsibility
- Diagnose and fix CI failures non-interactively: triage GitHub Actions logs, propose minimal fix plan, pair with
planningbefore code changes — do not touch secrets. - Drive PR/MR lifecycle: push branch, draft PR/MR from template or fallback, address review/comment threads, resolve merge conflicts, manage worktrees per writer for swarms (isolated branches, SHA-validated handoffs).
- Wire integrations: MCP providers (
setup/list/doctor), Slack (app vs workspace), Linear cycles/docs, ClickUp tasks/sprints — confirm targets viacapabilities/targets/registry.yaml(docs/TARGET_CAPABILITY_MATRIX.md). - Operate runtime: loops (
loop-runner), swarms (launch/observe/handoff), triage workstation health (triage), advise LLM cost/provider viallm-cost-advisor. - Own incident drafting (
delivery/incident) when production/user impact threshold met — coordinate withqa-engineerbug input andsecurity-engineerif security-sensitive. - Review/design CLI ergonomics for agents (
cli-for-agents) — non-interactive,gh/glabfriendly, allowlisted tooling.
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 · 134 lines · 2,398 tokens per session scan A b62d9fe2de2d
platform-engineer is a cursor rule published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed 4d ago), licensed MIT. It adds 2,398 tokens to every session, about $0.0120 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 2026-08-30.
Other cursor rules, from other repositories
test-case-to-katalon-studio
Convert Katalon True Platform/TestOps manual test cases into Katalon Studio automation inside a local Studio Test Project checkout. Use when you need to author or extend a .tc test case file and its paired Groovy script under Scripts/, keep test case variable GUIDs consistent with the .ts test suite bindings that read…
solana-transaction-safety
Safe Solana transaction submission patterns using Helius Sender.
execute-test
Execute Katalon True Platform/TestOps tests when the input is an existing test case, manual test case list, test suite, suite collection, execution request, or "run with AI" instruction. Use when you need to create a manual test run, start Run with AI, poll AI session results, schedule automated suites, read…
devops-infrastructure
DevOps and infrastructure: Docker, Kubernetes, Terraform, CI/CD. Load when editing Dockerfiles, compose, k8s manifests, Terraform, or workflow YAML — not for application code.
session-preflight
Require a visible session preflight before side-effecting agent work.
tell-local-ci-only
Prefer local verification; never wait on or drive GitHub Actions CI.