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 skills add natuleadan/skills --skill platformgit clone --depth 1 https://github.com/natuleadan/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/skills/natuleadan/skills/platform)<a href="https://agentmods.dev/skills/natuleadan/skills/platform"><img src="https://agentmods.dev/badge/skills/natuleadan/skills/platform/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/skills/natuleadan/skills/platform"><img src="https://agentmods.dev/badge/skills/natuleadan/skills/platform.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 | $0.00035 | $0.00366 |
| Opus 5.5 | $0.00014 | $0.00146 |
| Sonnet 5.5 | $0.00007 | $0.00073 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
platform 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 1mo 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.
What it actually says
Platform
How to work with the platform APIs: the service categories, how a call flows, authentication, scheduling, and human-in-the-loop.
Status: early. This skill describes what already exists; sections expand as the platform evolves.
Service categories
| Category | What it is | How you call it |
|---|---|---|
| Agent | Consumes a toolset and performs tasks | by its slug |
| Toolset | A bundle of tools invoked together (code XXX-P01) |
tool call per capability |
| Robot | Physical automation (code XXX-R01, area prefix) |
by its slug |
How a call flows
A request enters the API, the agent resolves the toolset, the tool runs, and the result is returned. Long operations return a job handle to poll.
Authentication
- API key or OAuth 2.1 for robots.
- The caller identity determines which agents and tools are reachable.
Scheduling
A user books a slot on an agent; the booking becomes a reservation. Availability is read before booking.
Human-in-the-loop
Critical operations require a human to confirm before they run. HIL is triggered by the operation type, not by the caller.
References
references/agent-types.md— categories and how each is addressedreferences/api-usage.md— request flow, jobs, and errorsreferences/scheduling.md— bookings and availabilityreferences/hil.md— human-in-the-loop rules
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 48 lines · 35 tokens per session scan A e1e60b02e7b0
platform is a skill published in the GitHub repository natuleadan/skills (3 stars, last pushed 25d ago), licensed Apache-2.0. It adds 35 tokens to every session and 366 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-21.
Other skills, from other repositories
httpie
Use this skill whenever the user wants to make HTTP requests, test APIs, call REST endpoints, debug web services, or interact with any HTTP/HTTPS API using the HTTPie CLI tool (http command). Trigger this skill for any request involving: sending GET/POST/PUT/PATCH/DELETE requests, testing API endpoints, sending JSON…
MCP Integration Assistant
Helps design and implement Model Context Protocol (MCP) server integrations for AI agents.
api-testing
REST/GraphQL API testing with automated validation — test endpoints, validate responses, check status codes, and ensure API contracts.
convex-agents
Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration.
backend-systems-guidance
Canonical overlay for non-trivial server-side networked implementation and review involving multi-layer architecture, data access, reliability, trust boundaries, or deeper testing; use backend-guidance for thin routine handlers. Compose with matching implementation guidance for APIs, queues, repositories…
backend-guidance
Baseline overlay for routine thin HTTP, gRPC, or message-consumer implementation and review; use backend-systems-guidance for multi-layer, data-access, transaction, reliability, or trust-boundary work. Compose with matching implementation guidance. Not for outbound-client-only or security-audit tasks.