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.
git clone --depth 1 https://github.com/athola/claude-night-marketWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/athola/claude-night-market/bloat-scan)<a href="https://agentmods.dev/commands/athola/claude-night-market/bloat-scan"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/bloat-scan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/athola/claude-night-market/bloat-scan"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/bloat-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.02521 |
| Opus 5 | $0.00000 | $0.01260 |
| Sonnet 5 | $0.00000 | $0.00504 |
| Haiku 4.5 | $0.00000 | $0.00252 |
Grade A, and why
bloat-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 8d 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 — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bloat Scan Command
Execute progressive bloat detection across code, documentation, and dependencies.
Usage
# Quick scan (Tier 1, default)
/bloat-scan
# Targeted analysis (Tier 2)
/bloat-scan --level 2
/bloat-scan --level 2 --focus code
/bloat-scan --level 2 --focus docs
# Deep audit (Tier 3)
/bloat-scan --level 3 --report audit-report.md
# Dry run (no changes)
/bloat-scan --dry-run
Options
| Option | Description | Default |
|---|---|---|
| `--level <1 | 2 | 3>` |
--focus <type> |
Focus area: code, docs, deps, or all |
all |
--report <file> |
Save report to file | stdout |
--dry-run |
Preview findings without taking action | false |
--exclude <pattern> |
Additional exclude patterns beyond defaults | .bloat-ignore |
--growth [path] |
Run growth velocity analysis on path | cwd |
--threshold <lines> |
Override default line limit for threshold alerts | varies by file type |
--compare |
Compare before/after optimization (use with --growth) |
false |
Note: Cache directories (.venv/, node_modules/, .pytest_cache/, etc.) are automatically excluded from all scans.
Scan Tiers
Tier 1: Quick Scan (2-5 min)
Detects:
- Large files (> 500 lines)
- Stale files (unchanged 6+ months)
- Commented code blocks
- Old TODOs (> 3 months)
- Zero-reference files
Requirements: None (heuristics and git)
Tier 2: Targeted Analysis (10-20 min)
Detects:
- Dead code (static analysis)
- Duplicate patterns
- Import bloat
- Documentation similarity
- Code churn hotspots
Requirements: Optional static analysis tools (Vulture, Knip)
Tier 3: Deep Audit (30-60 min)
Detects:
- All Tier 1 + Tier 2
- Cyclomatic complexity
- Dependency graphs
- Bundle size analysis
- Readability metrics
Requirements: Full tooling suite
Workflow
-
Invoke Command
/bloat-scan --level 2 --focus code -
Agent Executes Scan
- Dispatches
bloat-auditoragent - Loads
bloat-detectorskill modules - Runs detection algorithms
- Dispatches
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.
- 8d ago First seen · 362 lines · 0 tokens per session scan A 072409a73ad1
bloat-scan is a command published in the GitHub repository athola/claude-night-market (337 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,521 tokens. 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 2026-09-03.
Other commands, from other repositories
bug-detective
Systematic debugging assistant with troubleshooting steps.
bug-fix
Streamlines bug fixing by creating a GitHub issue first, then a feature branch for implementing and thoroughly testing the solution before merging.
debug-user-tx
Reproduce and debug a user-reported failing transaction against forked cluster state, mapping the failure back to source code.
test-and-fix
Run tests and automatically fix common issues.
doctor
Health check for the dev environment and solana-ai-kit config — read-only, with one exact fix-it command per failure.
debug-helper
Use when something is broken and you need it diagnosed. A build failure, a runtime crash, a blank page, an unreadable error message, or behaviour that is simply wrong. Gives one exact fix, not a list of things to try.