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 babyworm/rtl-agent-team --skill rat-dse-policygit clone --depth 1 https://github.com/babyworm/rtl-agent-teamWrote 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/babyworm/rtl-agent-team/rat-dse-policy)<a href="https://agentmods.dev/skills/babyworm/rtl-agent-team/rat-dse-policy"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/rat-dse-policy/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/babyworm/rtl-agent-team/rat-dse-policy"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/rat-dse-policy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00020 | $0.03057 |
| Opus 5 | $0.00010 | $0.01528 |
| Sonnet 5 | $0.00004 | $0.00611 |
| Haiku 4.5 | $0.00002 | $0.00306 |
Grade A, and why
rat-dse-policy 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 7d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DSE Policy
What Makes DSE Different from Standard Phase 1→3
| Aspect | Standard (p1 + p2 + p3 sequential) | rat-dse |
|---|---|---|
| Algorithm study | Select best, justify | Explore N candidates, quantitative comparison |
| Architecture | Single architecture from requirements | Multiple candidates, trade-off matrix, user selects |
| μArch + BFM | Single-pass μArch design | Iterative μArch with self-critique and re-exploration |
| Ref C model | Build from scratch | Accept functional model as input, transform to architectural model |
| Fixed-point | Identify precision requirements | Simulate effects, precision vs area trade-off curves |
| Iteration | One-shot per phase | Self-critique → re-run → user review → trial comparison |
| Output | Ready for Phase 4 | Pre-implementation package with DSE rationale, ready for Phase 4 |
Design Priority Order
- Functional Correctness (highest) — Every required feature works exactly
- Interface Compliance — Ports, protocols, timing match Architecture
- Timing/Performance — Throughput, latency targets met
- Area/Power (lowest)
Document-as-Memory
All exploration results captured in design artifacts (docs/, reviews/) so downstream phases can reference DSE rationale without repeating exploration.
DSE Methodology
Algorithm Comparison Matrix (per functional block)
For each major functional block, enumerate 2-4 algorithmic approaches:
| Metric | Candidate A | Candidate B | Candidate C |
|---|---|---|---|
| Computational complexity (ops/input) | |||
| Memory access pattern (seq/random, R/W ratio) | |||
| Memory bandwidth estimate | |||
| HW gate count estimate (order of magnitude) | |||
| Quality/accuracy impact (PSNR/SSIM if applicable) | |||
| Parallelization potential (data/pipeline) |
Fixed-Point Feasibility Analysis
- Minimum bit-width for acceptable precision
- Rounding mode impact (truncate vs round-half-up vs convergent)
- Precision vs area trade-off (e.g., 12-bit vs 16-bit internal paths)
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.
- 7d ago First seen · 278 lines · 20 tokens per session scan A 4d8cb0fab8ab
rat-dse-policy is a skill published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 18d ago), licensed MIT. It adds 20 tokens to every session and 3,057 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
hardware-health-check
Out-of-band hardware health via Redfish BMC (read-only) — power state, component health, thermal and power readings, firmware inventory, SEL log triage. Use when determining whether a host is powered off versus unreachable, checking hardware faults, reviewing thermal or PSU state, or triaging BMC event logs.
readable-verilog-generator
Use when creating, writing, reviewing, annotating, repairing, refactoring, or validating readable Verilog RTL, including synthesizable Verilog-2001 .v files, existing-RTL analysis, semantic comment annotation, testbench scaffold planning, ASIC-quality review, local or remote Vivado/xsim validation, evidence-backed…
hardware-saas-gtm
🇺🇸 Hardware + SaaS GTM Playbook — End-to-end go-to-market for consumer hardware products with software subscription models. Covers crowdfunding engineering (Kickstarter/Indiegogo/Makuake), KOL matrix for physical products, hardware PMF validation metrics, device-as-funnel subscription design, localization entry…
step-parts
Find, evaluate, and download low-level common standard CAD parts from step.parts, such as screws, bolts, nuts, washers, bearings, standoffs, electronics parts, motors, connectors, and other off-the-shelf components. Use when Codex needs to search the hosted step.parts catalog, resolve fuzzy part names, standards…
system-info
A skill for checking computer hardware, system status, running processes, and available disk space.
hdldiagzero
Generate validated SVG block diagrams for HDL/RTL/FPGA/SoC designs. Use when asked to draw, diagram, sketch, render, or visualize Verilog, SystemVerilog, VHDL, Vivado BD, or LiteX architecture. Produces JSON specs plus SVGs, color-codes clock domains, distinguishes AXI/MM/Lite/Stream and TileLink, and hides…