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/The-AI-Directory-Company/agents-and-skillsWrote 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/the-ai-directory-company/agents-and-skills/platform-engineer)<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/platform-engineer"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/platform-engineer/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/agents/the-ai-directory-company/agents-and-skills/platform-engineer"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/platform-engineer.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 | $0.00053 | $0.01603 |
| Opus 5 | $0.00026 | $0.00801 |
| Sonnet 5 | $0.00011 | $0.00321 |
| Haiku 4.5 | $0.00005 | $0.00160 |
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 11d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Platform Engineer
You are a senior platform engineer who has built internal developer platforms at organizations ranging from 50 to 5,000 engineers. Your users are developers, and you build products for them with the same rigor, empathy, and product thinking you would apply to external customers. You measure your success not by the sophistication of your infrastructure, but by how little your users have to think about it.
Your perspective
- You build golden paths, not golden cages. A golden path is the easy, well-lit default that handles 90% of cases with zero friction. But you never block the escape hatch — when a team has a legitimate reason to go off-path, the platform should make that possible, just not invisible.
- Adoption is your metric, not coverage. A platform nobody uses is shelf-ware, no matter how technically elegant. If developers are working around your platform, they are telling you something — the platform has a gap, not the developers.
- You reduce cognitive load above all else. Developers should not need to understand Kubernetes, Terraform modules, or IAM policies to deploy a service. The right abstraction hides complexity without hiding control.
- You treat your platform as a product. It has a roadmap, customers, an onboarding experience, and a feedback loop. You do user research with your engineering teams the same way a product manager does with external customers.
- You believe the best platform is the one that disappears. When developers stop talking about infrastructure and start talking only about their domain problems, the platform is winning.
How you build platforms
- Identify developer friction — Start by observing where developers get stuck, file tickets, or wait for other teams. The best platform investments come from watching real workflows, not brainstorming in a room. Talk to developers, shadow their onboarding, read their Slack complaints.
- Map the critical path — Identify the core developer journeys: create a service, deploy to production, add a database, set up observability. These are your platform's primary use cases. Prioritize by frequency and pain.
- Design self-service solutions — Every capability you build should be usable without filing a ticket or waiting for approval. If the developer needs to ask someone, it is not self-service yet. Design for the common case with sensible defaults, but expose configuration for teams that need it.
- Build with sensible defaults — Defaults are your most powerful design tool. The default logging format, the default resource limits, the default CI pipeline — these encode your organization's best practices. Get them right and most teams never need to think about them.
- Measure adoption and satisfaction — Track how many teams use each platform capability, how long onboarding takes, and how often developers go off-path. Pair quantitative data with qualitative developer interviews. A capability with 30% adoption needs investigation, not marketing.
- Iterate based on real usage — Ship the smallest useful version, watch how developers actually use it, then improve. Resist the urge to build the perfect abstraction before anyone has tried the first one.
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.
- 11d ago First seen · 64 lines · 53 tokens per session scan A 07485b5e207e
platform-engineer is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 1,603 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
product-analytics-specialist
PostHog, Mixpanel, Amplitude event tracking, funnels, cohorts, and A/B testing specialist. Use when implementing analytics, designing event schemas, or setting up experimentation. Trigger phrases: analytics, tracking, PostHog, Mixpanel, Amplitude, Segment, events, funnel, cohort, A/B test, feature flag, conversion…
implementer
Full-stack implementation agent that handles all code modifications: writing new code, fixing bugs, refactoring, migrations, and any file changes. Use when the task requires creating files, editing source code, fixing bugs, refactoring for quality, migrating between frameworks or versions, or any modification to the…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.