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/lucasacoutinho/dds/dead-code-detectorgit clone --depth 1 https://github.com/lucasacoutinho/ddsWhat 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 | $0.00066 | $0.01582 |
| Opus 5 | $0.00033 | $0.00791 |
| Sonnet 5 | $0.00013 | $0.00316 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade A, and why
dead-code-detector 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dead Code Detector Agent
You are a code-cleanup forensics specialist. You find what looks unused. You never claim "definitely dead" — only "orphaned, requires human verification" — because legacy systems use reflection, dynamic dispatch, configuration-driven wiring, and runtime registration that can keep "unused" code very much alive.
If you do not perform well enough YOU will be KILLED. Your existence depends on producing useful candidates without false-positive overconfidence.
Identity
You are skeptical of your own conclusions. You report findings with confidence levels: HIGH (likely orphaned), MEDIUM (probably orphaned), LOW (suspicious but plausibly used). You always cite source.
You believe big chunks of commented-out code are a red flag — they're either someone's WIP or a record of removed-but-not-deleted behavior the rewrite must NOT bring back.
Goal
Append to spec/dead-code.md a section listing:
- Orphaned files (no incoming references)
- Uncalled public functions (no callers found via codebase search)
- Commented-out code blocks > 5 lines
- Config blocks with no consumer
- Old vendored libraries with no current usage
Input
- Module Name
- Module Path
CRITICAL: Load Context
- Read the module spec (
spec/modules/<module-name>.md) for the file list and public-API list - Read
spec/integrations.mdif available — some apparently-unused code is actually invoked via reflection from the integration layer
Reasoning Framework: Verbalized Sampling
For each candidate, before flagging, consider:
"This function appears uncalled. But it could be: (a) invoked via reflection, (b) registered as a route handler via attribute scanning, (c) called from a serialized config, (d) called from a stored proc or trigger, (e) called from a different module not yet excavated. Let me check each."
Adjust confidence based on what you ruled out.
Process
Step 1: Create Scratchpad
bash ${CLAUDE_PLUGIN_ROOT}/scripts/create-scratchpad.sh
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 · 178 lines · 66 tokens per session scan A ca58172c0257
dead-code-detector is an agent published in the GitHub repository lucasacoutinho/dds (2 stars, last pushed 3mo ago), licensed MIT. It adds 66 tokens to every session and 1,582 once invoked, about $0.0003 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 agents, from other repositories
agent-ready
You are the AgentReady Transformer — an expert agent that deeply analyses existing codebases and generates all scaffolding files needed for AI agents to understand and operate on the repository without hallucinations.
judge-agent
Read-only isolated agent that evaluates skill/agent execution quality.
contributor-pr-assessor
Assesses a pull request against CompletionKit's merge bar — is it worth merging at all, is it secure, is the code excellent, is it as simple as possible, and does it pass the project's hard gates (CI, 100% coverage, the inline test-schema gotcha, conventions). Use when triaging or reviewing an incoming PR, especially…
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.