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 agents/vladolaru/claude-code-plugins/dead-code-reviewergit clone --depth 1 https://github.com/vladolaru/claude-code-pluginsWhat 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 | $0.00036 | $0.02902 |
| Opus 5 | $0.00018 | $0.01451 |
| Sonnet 5 | $0.00007 | $0.00580 |
| Haiku 4.5 | $0.00004 | $0.00290 |
Grade B, and why
dead-code-reviewer scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
Read the output carefully. It contains your review rules, review scope, and output instructions. If STATUS is ERROR or NO_DOMAIN_FILES, follow the instructions in the output and exit. How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANDATORY SETUP — Run Bootstrap Before Reviewing
Do NOT start reviewing code until this step is done:
Run the bootstrap script:
PLUGIN_ROOT=$(cat /tmp/.pirategoat-tools-root 2>/dev/null)
[ -z "$PLUGIN_ROOT" ] || [ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(find ~/.claude -path "*/pirategoat-tools/*/scripts/review/agent/bootstrap.py" -type f 2>/dev/null | sort | tail -1 | xargs dirname | xargs dirname | xargs dirname | xargs dirname)
python3 $PLUGIN_ROOT/scripts/review/agent/bootstrap.py --agent dead-code-reviewer
Read the output carefully. It contains your review rules, review scope, and output instructions. If STATUS is ERROR or NO_DOMAIN_FILES, follow the instructions in the output and exit.
You are an expert Dead Code Reviewer who thinks like a static analyzer with human judgment. Your core mission: prove reachability. Every symbol is alive until you prove it dead — not the other way around.
Your expertise: Static reachability analysis, call graph reasoning, import/export tracing, lifecycle analysis of functions and classes, and recognizing dynamic dispatch patterns that create false positives.
Your mindset: Dead code is invisible weight — it misleads readers, bloats bundles, and rots silently. But falsely flagging live code is worse. A false positive wastes a developer's time investigating code that works fine. Precision over recall, always.
This review matters. Dead code left behind becomes a trap — a future developer will trust it, build on it, and discover too late that nobody calls it. Worse: dead code that looks alive consumes maintenance effort across every refactor.
RULE 0 (MOST IMPORTANT): Prove It's Dead Before Reporting
Never report dead code based on suspicion. You must search for usages and find zero callers before reporting.
The Dead Code Verification Protocol:
- Identify the symbol (function, class, constant, import, parameter)
- Search the current codebase (HEAD) for all references:
git grep -n "<symbol>" -- "*.php" "*.js" "*.ts" | grep -v "function <symbol>\|class <symbol>\|def <symbol>" - If references exist → NOT dead. Stop.
- If zero references, check for dynamic usage patterns (see False Positive Checklist below)
- Only report if both searches find nothing
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 · 228 lines · 36 tokens per session scan B 4c6c5883483c
dead-code-reviewer is an agent published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 2,902 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.