A headless workflow for Pango Design Suite FPGA projects. FPGA hardware designs can be compiled, checked through JTAG, programmed, and debugged without opening the graphical interface.

Use it to build bitstreams, scan JTAG device IDs, program SRAM or SPI flash, and run scripted ILA or virtual-I/O debugging.

It enables repeatable command-line work for building and programming Pango or Logos FPGA designs.

pds-flow — Skill for Claude Code and Codex by Renkos1

Install

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.

Any agent

npx skills add Renkos1/pango-mcp --skill pds-flow

Clone the repo

git clone --depth 1 https://github.com/Renkos1/pango-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/renkos1/pango-mcp/pds-flow.svg)](https://agentmods.dev/skills/renkos1/pango-mcp/pds-flow)

Your own site

<a href="https://agentmods.dev/skills/renkos1/pango-mcp/pds-flow"><img src="https://agentmods.dev/badge/skills/renkos1/pango-mcp/pds-flow.svg" alt="Measured on agentmods" height="20"></a>

Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,756 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.

Model	Per session	Once invoked
Fable 5.1	$0.00132	$0.02756
Opus 5	$0.00066	$0.01378
Sonnet 5	$0.00026	$0.00551
Haiku 4.5	$0.00013	$0.00276

Measured 6d ago against content hash 829225571fa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pds-flow 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 6d 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.

skills/pds-flow/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pango Design Suite — headless compile / scan / flash / debug

Everything PDS does from the GUI can be driven headlessly with a handful of console tools. This skill is the reference for the control tools, the project/constraint/bitstream file formats, and the exact cdt_ Tcl* so a fresh session can do the full workflow correctly. Device-specific values below (IDCODE, device name, flash part, install path) are EXAMPLES — swap for your part/install.

Toolchain bin dir: your PDS install, e.g. <PDS_INSTALL>\bin (pds_shell.exe, cdt_js.exe, cdt_cfg.exe, cdt_ins.exe, cdt_dbg.exe all live there).
Tested against PDS 2022.2-SP4.2; examples use Logos2 PG2L100H / FBG484 / -6.

For the exhaustive Tcl command list + ready-to-run scripts see reference/cdt-tcl-commands.md; for the .pds/.fdc/.sbit/.sfc formats and the build-stage internals see reference/pds-project-and-flow.md; for scripted ILA/virtual-IO debug see reference/debug-ila.md.

The control tools (+ the GUI to avoid)

tool	role	invocation
`pds_shell.exe`	headless flow engine (synth→map→pnr→bitstream)	`pds_shell.exe -project <x.pds> -run <action>`
`pds.exe`	Qt GUI — do NOT use for headless: `-project -run` opens the GUI and idles	(interactive only)
`cdt_js.exe`	JTAG download server (cable daemon)	`cdt_js.exe -port <N>` (default 65420)
`cdt_cfg.exe`	Fabric Configuration tool (the programmer; runs `cfg_*` Tcl)	`cdt_cfg.exe -file <script.tcl>`
`cdt_ins.exe`	Fabric Inserter (build a debug/ILA core → `.fic`)	`cdt_ins.exe -netlist <adf> ... -file <tcl>`
`cdt_dbg.exe`	Fabric Debugger (program + trigger + dump waveform; virtual-IO)	`cdt_dbg.exe -file <tcl>`

cdt_cfg/cdt_ins/cdt_dbg are Tcl interpreters; cdt_cfg/cdt_dbg connect to a running cdt_js over TCP. Start cdt_js once (it stays resident), then run any number of script invocations.

1) Compile (source → bitstream), headless

pds_shell.exe -project <design.pds> -run gen_bit_stream

Runs the full flow: compile → synthesize → device_map → place_route → report_timing → generate_bitstream. Output: generate_bitstream/<top>.sbit. Minutes, scales with the design.
Use pds_shell.exe, never pds.exe for this (pds.exe opens the GUI and hangs).
Valid -run targets: compile, synthesize, dev_map (note: NOT device_map), pnr (NOT place_route), report_timing, gen_bit_stream, report_power, gen_netlist. Use an early target (e.g. -run dev_map) for a fast compile+resource check without P&R.
pds_shell exits 0 even when a stage errors — never trust the exit code alone; grep the log for ^E: (errors are E:-prefixed) and for the success line The bitstream file is "...<top>.sbit".
Encryption caveat (some machines): if a transparent-encryption agent is present (e.g. a DLP/EDR tool that hooks file writes), files written by a monitored app (the GUI launched from Explorer) may be encrypted at rest — a GUI-built .sbit is then garbage to the programmer. Files written by an unmonitored process (anything you launch from a shell) stay plaintext. So always (re)build with pds_shell from a shell; never reuse the GUI's bitstream. Self-check the .sbit: a plaintext one must NOT contain the encryptor's ASCII marker in its header.
Stages leave dirs (compile/ synthesize/ device_map/ place_route/ report_timing/ generate_bitstream/ constraint_check/) — regenerable; gitignore them.

Read the full file on GitHub · 140 lines

Files

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.

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.

6d ago First seen · 140 lines · 132 tokens per session scan A 829225571fa9

Subscribe to this mod's changes

pds-flow is a skill published in the GitHub repository Renkos1/pango-mcp (0 stars, last pushed 8d ago), licensed Apache-2.0. It adds 132 tokens to every session and 2,756 once invoked, about $0.0007 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.

Hardware and IoT

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…

google/skills · 83 tokens

jetson-diagnostic

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

NVIDIA/skills · 30 tokens

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…

NVIDIA/skills · 236 tokens

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…

SnailSploit/Claude-Red · 113 tokens

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…

NVIDIA/skills · 94 tokens

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.

NVIDIA/skills · 50 tokens