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 agentmods add skills/fzhiyu1/chipforge-plugin/chipforgenpx skills add Fzhiyu1/chipforge-plugin --skill chipforgegit clone --depth 1 https://github.com/Fzhiyu1/chipforge-pluginWhat 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 | $0.00046 | $0.02053 |
| Opus 5 | $0.00023 | $0.01026 |
| Sonnet 5 | $0.00009 | $0.00411 |
| Haiku 4.5 | $0.00005 | $0.00205 |
Grade A, and why
chipforge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChipForge AI
AI-powered FPGA development toolkit for Verilog simulation and design analysis.
FPGA Development Workflow (MUST FOLLOW)
When user requests to design/implement a Verilog module, follow this workflow:
Phase 1: Knowledge Graph Setup
- Initialize knowledge graph:
chipforge-kg.exe init <project> - Add module nodes with properties (Signal type)
- Add state machine nodes if applicable (StateTransition type)
- Add relations between modules (RELATED, STATETRANSITION)
Phase 2: Implementation
- Create project directory structure:
rtl/,tb/ - Write RTL code in
rtl/directory - Write testbench in
tb/directory (include$dumpfileand$dumpvars)
Phase 3: Verification Loop
- Syntax check → Fix errors if any
- Compile → Fix errors if any
- Simulate → Generate VCD
- Analyze VCD → Check waveforms
- Fix issues → Repeat from step 8 if needed
Phase 4: Documentation
- Add simulation results to knowledge graph (SignalExample type)
- Link results to modules (EXAMPLES relation)
- Report final status to user
Workflow Diagram
[Init KG] → [Write Code] → [Syntax Check]
↓
[Fix Code] ← [Errors?]
↓ ↓ No
Yes [Compile]
↑ ↓
[Fix Code] ← [Errors?]
↓ No
[Simulate]
↓
[Analyze VCD]
↓
[Fix Code] ← [Issues?]
↓ No
[Update KG] → [Done]
IMPORTANT Rules
- NEVER skip syntax check before simulation
- ALWAYS generate VCD in testbench (
$dumpfile,$dumpvars) - ALWAYS analyze VCD after simulation
- ALWAYS update knowledge graph with results
Available Tools (ONLY use these, do NOT guess other tool names)
| Tool | Purpose |
|---|---|
iverilog.exe |
Verilog compiler |
vvp.exe |
Simulation runtime |
vcd2wavedrom.exe |
VCD to WaveJSON converter |
chipforge-kg.exe |
Knowledge graph CLI |
What ships with it
60 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.
- bin/chipforge-kg.exe 3516 KB
- bin/iverilog.bat 142 B runs code
- bin/iverilog/iverilog-vpi.exe 50 KB
- bin/iverilog/iverilog.exe 86 KB
- bin/iverilog/lib/ivl/blif-s.conf 96 B
- bin/iverilog/lib/ivl/blif.conf 96 B
- bin/iverilog/lib/ivl/blif.tgt 813 KB
- bin/iverilog/lib/ivl/cadpli.vpl 492 KB
- bin/iverilog/lib/ivl/include/constants.vams 1.3 KB
- bin/iverilog/lib/ivl/include/disciplines.vams 1.1 KB
- bin/iverilog/lib/ivl/ivl.exe 2234 KB
- bin/iverilog/lib/ivl/ivlpp.exe 131 KB
- bin/iverilog/lib/ivl/libbz2-1.dll 97 KB
- bin/iverilog/lib/ivl/libgcc_s_seh-1.dll 105 KB
- bin/iverilog/lib/ivl/libhistory8.dll 63 KB
- bin/iverilog/lib/ivl/libreadline8.dll 250 KB
- bin/iverilog/lib/ivl/libstdc++-6.dll 1977 KB
- bin/iverilog/lib/ivl/libtermcap-0.dll 44 KB
- bin/iverilog/lib/ivl/libwinpthread-1.dll 57 KB
- bin/iverilog/lib/ivl/null-s.conf 65 B
- bin/iverilog/lib/ivl/null.conf 18 B
- bin/iverilog/lib/ivl/null.tgt 90 KB
- bin/iverilog/lib/ivl/pcb-s.conf 95 B
- bin/iverilog/lib/ivl/pcb.conf 48 B
- bin/iverilog/lib/ivl/pcb.tgt 1635 KB
- bin/iverilog/lib/ivl/sizer-s.conf 97 B
- bin/iverilog/lib/ivl/sizer.conf 97 B
- bin/iverilog/lib/ivl/sizer.tgt 793 KB
- bin/iverilog/lib/ivl/stub-s.conf 96 B
- bin/iverilog/lib/ivl/stub.conf 49 B
- bin/iverilog/lib/ivl/stub.tgt 450 KB
- bin/iverilog/lib/ivl/system.vpi 2399 KB
- bin/iverilog/lib/ivl/v2005_math.vpi 335 KB
- bin/iverilog/lib/ivl/v2009.vpi 421 KB
- bin/iverilog/lib/ivl/va_math.vpi 267 KB
- bin/iverilog/lib/ivl/vhdl_sys.vpi 290 KB
- bin/iverilog/lib/ivl/vhdl_textio.vpi 478 KB
- bin/iverilog/lib/ivl/vhdl-s.conf 103 B
- bin/iverilog/lib/ivl/vhdl.conf 86 B
- bin/iverilog/lib/ivl/vhdl.tgt 5550 KB
- bin/iverilog/lib/ivl/vhdlpp.exe 515 KB
- bin/iverilog/lib/ivl/vlog95-s.conf 141 B
- bin/iverilog/lib/ivl/vlog95.conf 57 B
- bin/iverilog/lib/ivl/vlog95.tgt 729 KB
- bin/iverilog/lib/ivl/vpi_debug.vpi 119 KB
- bin/iverilog/lib/ivl/vvp-s.conf 150 B
- bin/iverilog/lib/ivl/vvp.conf 103 B
- bin/iverilog/lib/ivl/vvp.tgt 861 KB
- bin/iverilog/lib/ivl/zlib1.dll 116 KB
- bin/iverilog/libbz2-1.dll 97 KB
- bin/iverilog/libgcc_s_seh-1.dll 105 KB
- bin/iverilog/libhistory8.dll 63 KB
- bin/iverilog/libreadline8.dll 250 KB
- bin/iverilog/libstdc++-6.dll 1977 KB
- bin/iverilog/libtermcap-0.dll 44 KB
- bin/iverilog/libwinpthread-1.dll 57 KB
- bin/iverilog/vvp.exe 924 KB
- bin/iverilog/zlib1.dll 116 KB
- bin/vcd2wavedrom.exe 9285 KB
- bin/vvp.bat 137 B runs code
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.
- 2d ago First seen · 233 lines · 46 tokens per session scan A 64ed550dc8fd
chipforge is a skill published in the GitHub repository Fzhiyu1/chipforge-plugin (4 stars, last pushed 7mo ago), licensed MIT. It adds 46 tokens to every session and 2,053 once invoked, about $0.0002 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.