Borrowing it
Nothing to install: this file belongs to pogorelov-labs/flipper-ble-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pogorelov-labs/flipper-ble-mcp/main/.claude/skills/flipper/SKILL.mdgit clone --depth 1 https://github.com/pogorelov-labs/flipper-ble-mcpWrote 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/pogorelov-labs/flipper-ble-mcp/flipper)<a href="https://agentmods.dev/skills/pogorelov-labs/flipper-ble-mcp/flipper"><img src="https://agentmods.dev/badge/skills/pogorelov-labs/flipper-ble-mcp/flipper/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/pogorelov-labs/flipper-ble-mcp/flipper"><img src="https://agentmods.dev/badge/skills/pogorelov-labs/flipper-ble-mcp/flipper.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 | $0.00206 | $0.02030 |
| Opus 5 | $0.00103 | $0.01015 |
| Sonnet 5 | $0.00041 | $0.00406 |
| Haiku 4.5 | $0.00021 | $0.00203 |
Grade B, and why
flipper scanned grade B with 1 finding 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 10d 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.
Harvests environment variablesmediumData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
- **Don't dump secrets into the KB** — card UIDs/keys, EMV PANs, handshakes, credentials stay out (or are redacted). Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flipper Zero — KB-aware operating skill
The Flipper knowledge base in this repo is your memory; the flipper / flipper-control / flipper-ble MCP servers are your hands. This skill is the loop that ties them together so the system gets faster every session: read the KB before acting, drive the device safely, then pour what you learned back into the KB. Don't re-derive what a doc already records — and don't let a hard-won learning evaporate when the session ends.
Read CLAUDE.md (house style) once per session if you'll write to the KB. The deep "how to drive the device" knowledge already lives in resources/flipper-control-playbook.md and resources/flipper-ble-control.md — this skill routes to those rather than repeating them.
The operating loop — run EVERY Flipper task this way
1 · ORIENT (read before you touch the device)
Cheap reads first — they save device round-trips and prevent dead ends.
- Map the task to docs. Start at
llms.txt(token-lean doc map). Then narrow:- By use case: most requests map to a UC — resolve it in
uc-index.json(UC-ID → docs) or scanuse-cases-model.md. - By topic:
grep -rl "^domain: wifi" .(ornfc,bluetooth, …), then follow each doc'srelated:graph. - Read the matching guide/reference's TL;DR + body. The common ones are in
references/routine-index.md— open it for the task→doc→tools map. For any add-on task (Marauder / NRF24 / CC1101 / GPS), also open itshardware/board doc — physical gotchas (power, mounting, dual-SD, band limits) live there, not in the capability doc.
- By use case: most requests map to a UC — resolve it in
- Pre-flight the device & pick a transport. USB read:
mcp__flipper__status. BLE:mcp__flipper-ble__ping(andscanonly if it's not answering). Orientation manual:mcp__flipper-ble__playbook. Checkapp_lock_status/desktop_is_lockedbefore launching anything. One BLE central at a time — if the user's phone holds the Flipper, BLE says "not found"; they free the phone's app. - Choose the path with the data-first ladder (from the playbook): pure data read (
storage_read/list/device_info) → direct app-entry (app_launch name=<full .fap path>) → semantic action → batched blind nav (press_sequence+ one trailing screenshot) → screenshot loop (only for dynamic UI). Prefer reading an SD artifact over reading pixels. - The constraint that re-routes everything: apps that seize the USB serial (WiFi Marauder, other ESP32/UART apps) kill the USB MCP servers while running → drive them over BLE, and read results from the SD log, not the 128×64 screen. The worked exemplar is
wifi/marauder-mcp-scan.md.
What ships with it
3 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.
- 10d ago First seen · 67 lines · 206 tokens per session scan B f810156bacb0
flipper is a skill published in the GitHub repository pogorelov-labs/flipper-ble-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 206 tokens to every session and 2,030 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it B with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.