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 ic-star-tech/ccfoundry-agent-kit --skill verilog_rragit clone --depth 1 https://github.com/ic-star-tech/ccfoundry-agent-kitWrote 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/ic-star-tech/ccfoundry-agent-kit/verilog_rra)<a href="https://agentmods.dev/skills/ic-star-tech/ccfoundry-agent-kit/verilog_rra"><img src="https://agentmods.dev/badge/skills/ic-star-tech/ccfoundry-agent-kit/verilog_rra/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/ic-star-tech/ccfoundry-agent-kit/verilog_rra"><img src="https://agentmods.dev/badge/skills/ic-star-tech/ccfoundry-agent-kit/verilog_rra.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 | $0.00022 | $0.00771 |
| Opus 5.5 | $0.00009 | $0.00308 |
| Sonnet 5.5 | $0.00004 | $0.00154 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
verilog_rra 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 2mo 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verilog RRA Testbench Skill
Trigger
Use this skill when the user asks to build, verify, or test a Round Robin Arbiter (RRA) in Verilog, or when a Foundry requirement mentions RRA/verilog.
Capabilities
- Write a parametric Round Robin Arbiter module (Verilog-2001)
- Generate a self-checking testbench with pass/fail assertions
- Compile using
iverilogand simulate usingvvp - Parse simulation output to determine pass/fail
Implementation Guide
RRA Module (rra.v)
Use a mask-based approach for fair round-robin scheduling:
- Maintain a 4-bit mask register
- After granting bit[i], set mask to clear bits <= i
- Use lowest-set-bit extraction:
x & (~x + 1) - When masked_req is empty, wrap around to unmasked req
// Round Robin Arbiter - 4 bit (Verilog-2001)
module rra (
input wire clk,
input wire rst_n,
input wire [3:0] req,
output reg [3:0] grant
);
reg [3:0] mask;
reg [3:0] masked_req;
reg [3:0] sel;
function [3:0] lsb;
input [3:0] x;
begin
lsb = x & (~x + 4'b0001);
end
endfunction
always @(posedge clk or negedge rst_n) begin
if (!rst_n) begin
mask <= 4'b1111;
grant <= 4'b0000;
end else if (|req) begin
masked_req = req & mask;
if (|masked_req)
sel = lsb(masked_req);
else
sel = lsb(req);
grant <= sel;
case (sel)
4'b0001: mask <= 4'b1110;
4'b0010: mask <= 4'b1100;
4'b0100: mask <= 4'b1000;
default: mask <= 4'b1111;
endcase
end else begin
grant <= 4'b0000;
end
end
endmodule
Testbench (rra_tb.v)
- Use
$dumpfile/$dumpvarsfor waveform capture - Include reset sequence (rst_n=0 for 20ns, then rst_n=1)
- Test single requests, round-robin all-request, and no-request cases
- Print PASS/FAIL for each test case
- Print summary with
ALL_TESTS_PASSEDorSOME_TESTS_FAILED
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.
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.
- 2mo ago First seen · 100 lines · 22 tokens per session scan A d3cd69881791
verilog_rra is a skill published in the GitHub repository ic-star-tech/ccfoundry-agent-kit (24 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 771 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 2026-08-30.
verilog_rra compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| verilog_rraic-star-tech/ccfoundry-agent-kit | Skill | 24 | 5mo ago | MIT | A | 22 | Claude Code, Codex |
| rtl-p4-implement-policybabyworm/rtl-agent-team | Skill | 67 | 1mo ago | MIT | A | 23 | Claude Code |
| rtl-p4s-unit-test-policybabyworm/rtl-agent-team | Skill | 67 | 1mo ago | MIT | A | 26 | Claude Code |
| rtl-p4s-unit-testbabyworm/rtl-agent-team | Skill | 67 | 1mo ago | MIT | A | 43 | Claude Code |
| embedded-testing-patternsHermeticOrmus/LibreEmbed-Claude-Code | Skill | 50 | 28d ago | MIT | A | 62 | Claude Code |
| mavlink-integrationatretyak1985/swarmery | Skill | 7 | yesterday | Apache-2.0 | A | 86 | Claude Code |
| rtl-p4-implementbabyworm/rtl-agent-team | Skill | 67 | 1mo ago | MIT | A | 43 | Claude Code |