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 agents/ulises-jeremias/agent-toolkit/platform-engineergit clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitWrote 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/agents/ulises-jeremias/agent-toolkit/platform-engineer)<a href="https://agentmods.dev/agents/ulises-jeremias/agent-toolkit/platform-engineer"><img src="https://agentmods.dev/badge/agents/ulises-jeremias/agent-toolkit/platform-engineer.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 | $0.00088 | $0.02385 |
| Opus 5 | $0.00044 | $0.01192 |
| Sonnet 5 | $0.00018 | $0.00477 |
| Haiku 4.5 | $0.00009 | $0.00238 |
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 3d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
- 3d ago First seen · 129 lines · 88 tokens per session scan A 817380727526
platform-engineer is an agent published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed 5d ago), licensed MIT. It adds 88 tokens to every session and 2,385 once invoked, about $0.0004 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 agents, from other repositories
platform-architect
Platform architect owning build, CI, packaging, and publish pipeline integrity. For rea, owns GitHub Actions workflows, npm publish provenance, tarball-smoke gate, Changesets VP flow, the pnpm test script chain, and vitest pool/IPC config. Designs the pipeline that release-captain ships through.
devops-engineer
DevOps engineer. Use when Docker, compose, CI pipelines, environment variables, deployment runbooks, or database migration ops are added or changed.
debugger
Debugs errors, test failures, and unexpected behavior. Knows PromptScript architecture.
devops
Use proactively when user asks about CI/CD, GitHub Actions, deployment, or infrastructure. Manages pipelines, workflows, and PR automation.
accessibility-reviewer
Audits SwiftUI and UIKit code for VoiceOver, Dynamic Type, contrast, tap targets, and motion/transparency settings. Read-only — reports findings with file:line and the specific fix. Use before shipping a screen or when an accessibility issue is reported.
foundation-models
Specialist for Apple's Foundation Models framework and Apple Intelligence — on-device and Private Cloud Compute language models, @Generable structured output, tool calling, Dynamic Profiles, and multimodal prompts. Use when building, reviewing, or debugging any on-device LLM feature. Enforces availability gating and…