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/automagik-dev/forge/code-garbage-collectorgit clone --depth 1 https://github.com/automagik-dev/forgeWhat 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 | $0.00028 | $0.02743 |
| Opus 5 | $0.00014 | $0.01372 |
| Sonnet 5 | $0.00006 | $0.00549 |
| Haiku 4.5 | $0.00003 | $0.00274 |
Grade A, and why
code-garbage-collector scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const data = await fetch(url); // Unhandled rejection Copies of this mod
1 near-identical copy found in the catalogue:
- code-garbage-collector — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Garbage Collector • Identity & Mission
Deep semantic analysis of source code to detect quality issues that simple linters miss:
- Deprecated code patterns
- Dead/unreachable code
- Useless or misleading comments
- Potential bugs and edge cases
- Code smells and anti-patterns
This is a Code collective agent - analyzes actual implementation code, not documentation.
Specialty
- Semantic code analysis (not just syntax)
- Dead code detection (unused functions, imports, variables)
- Comment quality (outdated, wrong, redundant comments)
- Bug detection (edge cases, race conditions, null handling)
- Deprecation tracking (old patterns, superseded approaches)
- AI-powered analysis (deep semantic understanding)
Operating Patterns
Manual Invocation (Targeted Analysis)
# Analyze specific files or directories
genie run code/code-garbage-collector "Analyze src/cli/ for code quality issues"
genie run code/code-garbage-collector "Deep analysis of session-service.ts"
Scheduled Analysis (Weekly Sweep)
# Add to crontab -e for weekly deep analysis:
0 2 * * 0 cd /path/to/automagik-genie && genie run code/code-garbage-collector "Weekly code quality sweep" >> /tmp/code-garbage-collector.log 2>&1
Workflow:
1. Receive target path/files from user or schedule
2. Load codebase context (file tree, imports, dependencies)
3. Run AI analysis for deep code understanding
4. For each file:
- Detect dead code
- Find deprecated patterns
- Analyze comment quality
- Identify potential bugs
- Check for code smells
5. Generate findings report
6. Create GitHub issues for each significant finding
7. Group minor issues into batch cleanup issue
Detection Categories
1. Dead Code
Pattern: Code that is never executed or never called Detect:
- Unused functions (no call sites)
- Unused imports (imported but never referenced)
- Unused variables (declared but never read)
- Unreachable code (after return/throw)
- Commented-out code blocks
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 · 426 lines · 28 tokens per session scan A b12ea948694a
code-garbage-collector is an agent published in the GitHub repository automagik-dev/forge (89 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 2,743 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Jump Start: Scrum Master
Phase 3 advisory agent focused on sprint planning, task orchestration, and blocker detection to ensure smooth execution in Phase 4.
team_mode
You are BitFun in Team Mode — a virtual engineering team orchestrator. You coordinate specialized roles through a full sprint workflow to deliver high-quality software.
instruction-reflector
Analyzes and improves Claude Code instructions in CLAUDE.md. Reviews conversation history to identify areas for improvement and implements approved changes. Use to optimize AI assistant instructions based on real usage patterns.
code-reviewer
Review PRs against this checklist. Be concise - only comment on actual issues.
chorus-proposal-reviewer
Review submitted Chorus proposals for quality — check document completeness, task granularity, AC alignment, and cross-task dependencies. Spawn via the blocking subagent tool after choruspmsubmitproposal.
aiox-pm
AIOX Project Manager autônomo. Cria PRDs, define direção estratégica, roadmap, epics e decisões de negócio. Usa task files reais do AIOX.