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/jeffrigby/somepulp-agents/dead-codegit clone --depth 1 https://github.com/jeffrigby/somepulp-agentsWhat 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 | $0.00753 |
| Opus 5 | $0.00008 | $0.00377 |
| Sonnet 5 | $0.00003 | $0.00151 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
dead-code 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 yesterday.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dead Code Detection
Analyze the project for dead code using automated tools with agent verification.
Mode
$ARGUMENTS
- detect (default): Find and report dead code, no modifications
- cleanup: Find dead code, then offer to remove after user approval
Tools Used
- JavaScript/TypeScript: knip (
npx knip) - Python: deadcode (
pip install deadcode)
Project type is auto-detected from package.json, tsconfig.json, requirements.txt, or pyproject.toml.
IMPORTANT: False Positive Handling
Dead code tools return many false positives. The agent MUST verify each finding before reporting:
Verify Before Reporting
For each flagged item:
- Read the flagged code to understand its context
- Check for dynamic references:
import(variable),require(variable), reflection - Check framework patterns: React components, decorators, middleware
- Check re-exports: Is this in an index.ts barrel file for public API?
- Check entry points: CLI scripts, serverless handlers, workers
Common False Positives to Filter
- Dynamic imports:
import(modulePath),require(variableName) - React/Vue components used in JSX/templates
- Decorated classes (Angular, NestJS, Python decorators)
- Re-exports for public API in index files
- Entry points configured outside standard patterns
- Test utilities only used in test files
- CLI scripts or serverless handlers
Workflow
- Invoke the
dead-code-cleanupagent to run detection and verification:- The agent runs the detection tool via
"${CLAUDE_PLUGIN_ROOT}"/scripts/dead-code-detect.sh - It parses findings into categories and verifies each item (reads code, filters false positives)
- It returns a verified report plus a proposed cleanup plan grouped by confidence (safe / needs-review)
- The agent runs the detection tool via
- Present the returned report and plan to the user
- If cleanup mode: use AskUserQuestion to ask which groups to remove
- Apply only the approved removals
Report Format
Present findings as:
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.
- yesterday First seen · 91 lines · 16 tokens per session scan A cc39adf5a997
dead-code is a command published in the GitHub repository jeffrigby/somepulp-agents (7 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 753 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
audit
Run one selected Whats.Going.On. reviewer, or all selected reviewers in dependency waves.
operationalize
Turn an approved synthesis into explicitly untested, source-linked operator aids without executing procedures or changing systems.
cost
Produce a reconciled API-equivalent cost estimate for a completed Whats.Going.On. audit.
summarize
Reconcile completed Whats.Going.On. reviewers and create decision-grade audience reports.
upload
Verify a completed public WGO audit and open a draft PR in the configured report repository.
audit
Full project audit with Health Score, findings, and a prioritized fix plan.