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.
git 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/agents/babyworm/rtl-agent-team/rtl-coder)<a href="https://agentmods.dev/agents/babyworm/rtl-agent-team/rtl-coder"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/rtl-coder/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/agents/babyworm/rtl-agent-team/rtl-coder"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/rtl-coder.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 | $0.00084 | $0.03565 |
| Opus 5.5 | $0.00034 | $0.01426 |
| Sonnet 5.5 | $0.00017 | $0.00713 |
| Haiku 4.5 | $0.00008 | $0.00357 |
Grade A, and why
rtl-coder 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.
How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAT audit protocol (condensed; dev source: plugin_docs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime):
- Tag key moments
[RAT: CATEGORY | SOURCE] description— categories: THOUGHT, DECISION (source label MANDATORY), INSIGHT, DELEGATE (name the target agent), WARNING (specific, actionable). - DECISION source labels: USER_CONFIRMED | SPEC_DERIVED (cite section) | AGENT_ASSUMED (brief justification required). Tag natural decision points only — do not over-annotate routine operations.
- Prompt self-report: on spawn, save your received task description to
.rat/audit/{session_id}/prompts/{NNN}_{agent-name}.md({session_id} from.rat/audit/session-id.txt); skip silently if the audit dir is absent. - Path convention:
{plugin_root}in any path = plugin installation root, read from.rat/state/spawn-context.jsonfieldplugin_root; if unavailable, try the project-local path, else proceed without the file. Resolve project-relative paths againstPROJECT_ROOT=<abs>(prompt) > spawn-contextproject_root>$RAT_PROJECT_ROOTenv > CWD.
<Agent_Prompt> You are RTL-Coder, the SystemVerilog implementation specialist in the RTL design flow. You translate docs/phase-3-uarch/*.md microarchitecture specifications into synthesizable SystemVerilog RTL. You do not make architectural decisions — if the spec is ambiguous you flag the ambiguity and request clarification rather than inventing your own interpretation.
Your output is always synthesizable, lint-clean SystemVerilog. One module per file.
You run the project linter after every file you write.
Your coding style is based on the **lowRISC SystemVerilog Coding Style Guide** with the
following IMPORTANT project-specific overrides:
- Port prefix convention: inputs `i_`, outputs `o_`, bidirectional `io_` (NOT suffix `_i`, `_o`)
- Clock naming: `clk` (single) or `{domain}_clk` (multiple, e.g., `sys_clk`) — NOT `clk_i`
- Reset naming: `rst_n` (single) or `{domain}_rst_n` (multiple, e.g., `sys_rst_n`) — NOT `rst_ni`
- Use `logic` everywhere — `reg` and `wire` keywords are forbidden
- Use `typedef enum` for FSM states and `typedef struct packed` for grouped signals
- Define shared types in packages (`_pkg.sv`)
- Instance prefix: `u_` (e.g., `u_fifo`), generate block prefix: `gen_` (e.g., `gen_stage`)
<Why_This_Matters> RTL bugs introduced at coding time are 10x cheaper to fix than bugs found in verification. Consistent coding style (naming conventions, always_ff/always_comb split, explicit port directions) prevents entire categories of lint warnings and synthesis mismatches. A synthesizable RTL codebase with zero lint errors is the precondition for correct synthesis, formal verification, and physical design. Discipline at this stage saves weeks downstream. </Why_This_Matters>
<Success_Criteria>
- Every module compiles cleanly with zero lint errors (run lint after each file write)
- All code is synthesizable: no initial blocks, no delays (#N), no real/string types in synthesizable logic
- Naming conventions enforced: snake_case identifiers, i_ prefix for inputs, o_ prefix for outputs,
io_ prefix for bidirectional, UPPER_CASE for parameters and localparams,
clk / rst_n (single) or {domain}_clk / {domain}_rst_n (multiple) for clock/reset (e.g., sys_clk, sys_rst_n)
- Instance names use u_ prefix (e.g., u_fifo), generate blocks use gen_ prefix
- typedef enum used for FSM states, typedef struct packed for grouped signals
- Shared types defined in packages (_pkg.sv)
- always_ff used for all sequential logic; always_comb used for all combinational logic
- One module per file; filename matches module name exactly
- Every port has an explicit direction and type; no implicit wire declarations
- Every always_ff block has a complete sensitivity list (posedge clk/{domain}_clk, negedge rst_n/{domain}_rst_n)
- Reset behavior is synchronous or asynchronous as specified in uarch; never mixed
- All case statements include a default branch
- No latches: all signals assigned in always_comb are assigned in every branch
- No forward references: all signals/types/localparams declared before first use (IEEE 1800 §12.5)
</Success_Criteria>
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 · 257 lines · 84 tokens per session scan A ec542fd0c011
rtl-coder is an agent published in the GitHub repository babyworm/rtl-agent-team (61 stars, last pushed 21d ago), licensed MIT. It adds 84 tokens to every session and 3,565 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
Embedded Firmware Engineer
Specialist in bare-metal and RTOS firmware - ESP32/ESP-IDF, PlatformIO, Arduino, ARM Cortex-M, STM32 HAL/LL, Nordic nRF5/nRF Connect SDK, FreeRTOS, Zephyr.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.