Skip to content
Agentmart
Submit a tool

rat-plugin-debug

Plugin diagnostics: version, EDA tool status, state files, hook health.

Skill by babyworm

IndexedMIT★ 61
Write a review

Chalk Labs

Need help deploying rat-plugin-debug?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/babyworm-rat-plugin-debug

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Plugin diagnostics: version, EDA tool status, state files, hook health. Triggers: 'rat debug', 'plugin status', troubleshooting plugin behavior.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/rat-plugin-debug

Tools it pre-approves 4

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Bash,
  • Read,
  • Glob,
  • Grep

What's inside

Skill name
rat-plugin-debug
Description
Plugin diagnostics: version, EDA tool status, state files, hook health. Triggers: 'rat debug', 'plugin status', troubleshooting plugin behavior.
License
MIT
Allowed tools
Bash,, Read,, Glob,, Grep
Instructions
177 lines in SKILL.md · view on GitHub

Before installing

  • Pre-approves some shell commands

Files (1)

  • SKILL.md

SKILL.md (first lines)

<Purpose>
Display RTL Agent Team plugin diagnostics for debugging and environment verification.
Shows plugin version, EDA tool availability, state file status, and hook health.
</Purpose>

<Use_When>
- Debugging plugin issues or unexpected behavior
- Verifying EDA tool installation status
- Checking plugin state files for stale or corrupt entries
- User says "debug", "diagnostics", "plugin status", "rat debug"
</Use_When>

<Do_Not_Use_When>
- Setting up a new project (use rat-init-project) or installing tools (use rat-setup)
- Running design pipeline (use rat-auto-design or phase-specific skills)
</Do_Not_Use_When>

## Execution

Run each diagnostic section and present a consolidated report. All checks are read-only and non-destructive.

### 1. Plugin Version

```bash
# Read plugin version from manifest
grep -m 1 '"version"' "${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json" 2>/dev/null
# Fallback: check if CLAUDE_PLUGIN_ROOT is set
echo "CLAUDE_PLUGIN_ROOT=${CLAUDE_PLUGIN_ROOT:-NOT_SET}"
```

Report: `rtl-agent-team v{version}` and plugin root path.

### 2. EDA Tool Status

Check each tool and report version or NOT_FOUND. Group by classification:

```bash
first_line_or_not_found() {
  local tool="$1"
  local output
  local rc
  shift
  if ! command -v "$tool" >/dev/null 2>&1; then
    echo "NOT_FOUND"
    return 127
  fi
  if output="$("$@" 2>&1)"; then
    printf '%s\n' "$output" | sed -n '1p'
  else
    rc=$?
    printf '%s\n' "$output" | sed -n '1p' >&2
    return "$rc"
  fi
}

# --- Required ---
first_line_or_not_found verilator verilator --version
first_line_or_not_found python3 python3 --version
python3 -c "import cocotb; print('cocotb', cocotb.__version__)" 2>&1 || echo "NOT_FOUND"
first_line_or_not_found g++ g++ --version
first_line_or_not_found make make --version
pkg-config --modversion systemc 2>/dev/null || (test -n "$SYSTEMC_HOME" && test -d "$SYSTEMC_HOME" && echo "systemc via SYSTEMC_HOME=$SYSTEMC_HOME") || echo "NOT_FOUND"

# --- Lint tools (at least one required) ---
first_line_or_not_found verible-verilog-lint verible-verilog-lint --version
first_line_or_not_found slang slang --version

# --- CDC tools (at least one required) ---
first_line_or_not_found svlens svlens --version
for tool in sg_shell vc_cdc questa_cdc; do
  command -v "$tool" 2>/dev/null || echo "NOT_FOUND"
done

# --- Recommended ---
first_line_or_not_found slang-server slang-server --version
jq --version 2>&1 || echo "NOT_FOUND"

# --- Optional ---
first_line_or_not_found iverilog iverilog -V
first_line_or_not_found yosys yosys --version
first_line_or_not_found sby sby --help
first_line_or_not_found gtkwave gtkwave --version
first_line_or_not_found docker docker --version
```

Report as a table with status icons: `[OK]` installed, `[!!]` required but missing, `[--]` optional and missing.

### 3. Project Setup Status

```bash
# Check if rat-init-project has been run (marker: .claude/rules/rtl-coding-conventions.md)
test -f .claude/rules/rtl-coding-conventions.md && echo "SETUP_DONE" || echo "SETUP_NOT_DONE"

# Check directory structure
for dir in specs refc rtl sim lint syn docs reviews .rat/state; do
  test -d "$dir" && echo "[OK] $dir" || echo "[--] $dir"
done

# Check deployed rules
for f in .claude/rules/rtl-coding-conventions.md .claude/rules/rtl-verification-gate.md; do
  test -f "$f" && echo "[OK] $f" || echo "[--] $f"
done
# Diagram rules: check global CLAUDE.md tag OR local fallback file
grep -q '<markdown_diagram_rule>' ~/.claude/CLAUDE.md 2>/dev/null && echo "[OK] diagram-rules (global CLAUDE.md tag)" || \
  (test -f .claude/rules/diagram-rules.md && echo "[OK] diagram-rules (local file)" || echo "[--] diagram-rules (neither global tag nor local file)")

# Check deployed guides
for f in rtl/CLAUDE.md sim/CLAUDE.md docs/CLAUDE.md reviews/CLAUDE.md refc/CLAUDE.md syn/CLAUDE.md; do
  test -f "$f" && echo "[OK] $f" || echo "[--] $f"
done
```

### 4. State Files

```bash
# List all state files with age
find .rat/state/ -name "*.json" -type f 2>/dev/null | while read f; do
  AGE_SEC=$(( $(date +%s) - $(stat -c %Y "$f" 2>/dev/null || stat -f %m "$f" 2>/dev/null || echo 0) ))
  AGE_MIN=$(( AGE_SEC / 60 ))

From babyworm/rtl-agent-team, MIT.

More from babyworm/rtl-agent-team

Signals

Stars
61
Forks
16
Open issues
0
Last commit (this folder)
Jul 17, 2026 (3 months ago)
Last release
Jul 17, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from babyworm

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get rat-plugin-debug running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying rat-plugin-debug?

CallGet help
Cite this page

rat-plugin-debug skill. Agent Mart. https://agentmart.dev/skills/babyworm-rat-plugin-debug (last updated 2026-10-24)