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 commands/mathisk2095/jko-claude-plugins/dead-code-scangit clone --depth 1 https://github.com/mathisk2095/jko-claude-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 | $0.00016 | $0.01688 |
| Opus 5 | $0.00008 | $0.00844 |
| Sonnet 5 | $0.00003 | $0.00338 |
| Haiku 4.5 | $0.00002 | $0.00169 |
Grade A, and why
dead-code-scan 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dead Code Scan
Comprehensive scan for dead code across the project. Reports findings without making changes. Use /dead-code-clean to actively remove.
CRITICAL: This is a scan, not a fix. Document issues thoroughly with clear evidence and confidence levels. Use /dead-code-clean to remove issues after the scan.
First: Use the dead-code-expert skill for detection catalog, language tools, and false-positive awareness.
Preparation
- Detect the project language from file extensions and config files (package.json, Cargo.toml, pyproject.toml, go.mod, *.csproj, Package.swift).
- Identify entry points (main, index, App, etc.).
- Determine the target. If no target specified, scan from project root focusing on source directories.
Automated Scans
Run all applicable scans based on detected language.
Universal Scans (all languages)
# Debug artifacts
rg -c '(console\.log|print\(|dbg!\(|println!\(|debugger|breakpoint\(\)|System\.out\.print)' . --glob '!*test*' --glob '!*spec*' --glob '!node_modules*' --glob '!target*' --glob '!.git*' --glob '!__pycache__*' 2>/dev/null | awk -F: '{s+=$2} END {print "Debug artifacts:", s+0}'
# Lint suppressions hiding dead code
rg -c '(#\[allow\((dead_code|unused)|eslint-disable.*unused|# noqa: F4|@SuppressWarnings.*unused|#pragma warning disable)' . --glob '!node_modules*' --glob '!target*' 2>/dev/null | awk -F: '{s+=$2} END {print "Lint suppressions:", s+0}'
# Commented-out code (heuristic)
rg -c '^\s*(//|#)\s*(const|let|var|function|class|import|from|if|for|while|return|def |fn |pub |async |await )\b' . --glob '!node_modules*' --glob '!target*' 2>/dev/null | awk -F: '{s+=$2} END {print "Commented code:", s+0}'
# TODO/FIXME/HACK markers
rg -c '\b(TODO|FIXME|HACK|XXX|TEMP|TEMPORARY)\b' . --glob '!node_modules*' --glob '!target*' 2>/dev/null | awk -F: '{s+=$2} END {print "TODO/FIXME/HACK:", s+0}'
# Skipped tests
rg -c '(@skip|@ignore|xit\(|xdescribe\(|\.skip\(|#\[ignore\]|\[Ignore\]|@Disabled|@pytest\.mark\.skip)' . --glob '*test*' --glob '*spec*' 2>/dev/null | awk -F: '{s+=$2} END {print "Skipped tests:", s+0}'
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 · 148 lines · 16 tokens per session scan A 537487e4c919
dead-code-scan is a command published in the GitHub repository mathisk2095/jko-claude-plugins (3 stars, last pushed 4d ago), licensed MIT. It adds 16 tokens to every session and 1,688 once invoked, about $0.0001 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 commands, from other repositories
status
Show tlive daemon, channel, and Codex companion status.
codex-review
Run OpenAI Codex code review on current changes or a specific branch/commit.
stats
Show statistics for saved conversation files.
close
Close out a Linear issue — move to Done, add a closing comment, and clean up the local branch/worktree.
prompt
Convert a rough ask into a structured XML-tagged prompt using the factory-prompting vocabulary.
submit
Move the current branch's Linear issue to In Review.