agentmods.dev

Tiny-RF-Simulator: Skill for Claude Code

.agents/skills/using-rf-sim-mcp/SKILL.md

using-rf-sim-mcp is a skill for Claude Code, Codex from striderZA/Tiny-RF-Simulator. It costs 34 tokens per session (745 once invoked), scanned A, original, Apache-2.0.

Instructions for controlling an RF simulator through an MCP connection, a bridge that lets an agent call tools in another application. It covers circuit edits, measurements, sweeps, epochs, and simulator errors.

In plain words
What is it for?
Use it to read and edit an open RF Simulator project, run port measurements or network-analyzer sweeps, and handle bridge errors such as unavailable or busy simulator states.
Why use it?
It prevents invalid or stale edits by requiring the agent to inspect component parameters and the current project state before changing or measuring a circuit.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is striderZA/Tiny-RF-Simulator's own configuration. It tells Claude Code and Codex how to work on Tiny-RF-Simulator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Tiny-RF-Simulator configures →

not rated 44repo +2 changed 18d ago A scan 34 tokens original Apache-2.0
View source ↗ striderZA/Tiny-RF-Simulator
Reuse

Borrowing it

Nothing to install: this file belongs to striderZA/Tiny-RF-Simulator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/striderZA/Tiny-RF-Simulator/master/.agents/skills/using-rf-sim-mcp/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/striderZA/Tiny-RF-Simulator

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for using-rf-sim-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/striderza/tiny-rf-simulator/using-rf-sim-mcp/github.svg)](https://agentmods.dev/skills/striderza/tiny-rf-simulator/using-rf-sim-mcp)
Your own site
<a href="https://agentmods.dev/skills/striderza/tiny-rf-simulator/using-rf-sim-mcp"><img src="https://agentmods.dev/badge/skills/striderza/tiny-rf-simulator/using-rf-sim-mcp/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.

agentmods 80×15 button for using-rf-sim-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/striderza/tiny-rf-simulator/using-rf-sim-mcp"><img src="https://agentmods.dev/badge/skills/striderza/tiny-rf-simulator/using-rf-sim-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 745 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.00745
Opus 5.5 $0.00014 $0.00298
Sonnet 5.5 $0.00007 $0.00149
Haiku 4.5 $0.00003 $0.00075

Measured 18d ago against content hash 2058a6961234, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

using-rf-sim-mcp 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 18d 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.

.agents/skills/using-rf-sim-mcp/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using the rf-sim MCP server

Tools act on the open project. Use tools/list for arguments and reference.md for error and field details.

Before the first call

  • Enable Agent Server (View > Agent > Agent Server) or calls return SIMULATOR_UNAVAILABLE.
  • The catalog has 13 tools; report any missing from tools/list.
  • For library entries, call component_types {type}; create only when authorable is true and use non-file library_fields in library_create. It writes validated JSON only; no circuit placement, state/checkpoint changes, or overwrite. See the reference for roots and limits.
  • Only project_save/project_load read or write .rfsim; MCP offers no dialogs or checkpoint reverts.

Workflow

  1. circuit_get (include_params: true for values). Use each component's id, not its label number.
  2. Before changing a component, call component_get {epoch, component} for its param_info.
  3. Make changes in one circuit_edit (1 to 64 ops, applied in order). move takes an existing id and an absolute position; add.position places a new component.
  4. Measure with measure_port or network_analyzer_sweep. null means unavailable, never zero.

Epochs

  • Edits do not change epoch. revision advances only when an edit changes project state.
  • On STALE_EPOCH, re-read circuit_get: project ids restart at 100 and may be reassigned.
  • Panning changes positions, not epoch; re-read before moving.

Projects

  • project_save writes the open file, or path when given. project_load {epoch, path} replaces the circuit. Both use absolute .rfsim paths.
  • project_load returns UNSAVED_CHANGES while the project has unsaved edits. Save first, or ask the user to save or discard them.
  • A successful load clears checkpoints and changes the epoch. Call circuit_get afterwards.

circuit_edit rules

  • add takes a lowercase registry key; unknown types return UNKNOWN_TYPE.
  • Ops stop at first error, but earlier ops remain applied. Use op_index/applied, re-read, then send remaining work; confirm before retrying NOT_FOUND.
  • To rewire an occupied input (INPUT_OCCUPIED), put {op:"disconnect", to} before the connect in the same call.
  • PFB channelizer input 0 accepts only RF ADC output 0 (ADC_TO_PFB_ONLY). If no ADC exists, add one (type: "adc", with a ref) and route through it in the same call.

Read the full file on GitHub · 51 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 18d ago Changed · +1 lines · -46 tokens per session 2058a6961234
  2. 22d ago Changed · +4 tokens per session a9469db03e91
  3. 24d ago Changed · +2 lines · +11 tokens per session fae482c3ce2b
  4. 25d ago Changed · +2 lines b696548ed1cf
  5. 27d ago First seen · 46 lines · 65 tokens per session scan A 7b04b1a10a14

Subscribe to this mod's changes

using-rf-sim-mcp is a skill published in the GitHub repository striderZA/Tiny-RF-Simulator (44 stars, last pushed today), licensed Apache-2.0. It adds 34 tokens to every session and 745 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 2026-10-12.

C and C++Hardware and IoTScientificdspglfwimguirfsignal-processing
Related

using-rf-sim-mcp compared with skills from other repositories

using-rf-sim-mcp next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
using-rf-sim-mcpstriderZA/Tiny-RF-SimulatorSkill44todayApache-2.0A34Claude Code, Codex
ruview-advanced-sensingruvnet/RuViewSkill103ktodayMITA84Claude Code
ruview-applicationsruvnet/RuViewSkill103ktodayMITA79Claude Code
calibrate-roomruvnet/RuViewSkill103ktodayMITA41Claude Code
audio-calibration-engineerdaredoole/audio-calibration-mcpSkill86d agoMITA60Codex
signal-processingxjtulyc/awesome-rosetta-skillsSkill356mo agononeA29Claude Code, Codex
ruview-configureruvnet/RuViewSkill103ktodayMITA67Claude Code