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/unbloat)<a href="https://agentmods.dev/commands/athola/claude-night-market/unbloat"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/unbloat/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/unbloat"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/unbloat.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 | $0.00027 | $0.01703 |
| Opus 5 | $0.00014 | $0.00851 |
| Sonnet 5 | $0.00005 | $0.00341 |
| Haiku 4.5 | $0.00003 | $0.00170 |
Grade A, and why
unbloat 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 7d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unbloat Command
Execute safe bloat remediation workflows with user approval at each step.
When To Use
Use this command when you need to:
- After bloat-scan identifies remediation targets
- Preparing for release
- Reducing codebase complexity
When NOT To Use
- Quick fixes that don't need structured workflow
- Already know the specific issue - fix it directly
Philosophy
- Safety First: Every change requires explicit approval (no auto-changes without review)
- Progressive: Start with high-confidence, low-risk changes first
- Reversible: Creates backup branches with clear rollback instructions
Usage
# Integrated workflow: scan + remediate
/unbloat
# Use existing bloat-scan report
/unbloat --from-scan bloat-report.md
# Auto-approve low-risk changes (still shows preview)
/unbloat --auto-approve low
# Preview changes without executing
/unbloat --dry-run
# Focus on specific area
/unbloat --focus code
Options
| Option | Description | Default |
|---|---|---|
--from-scan <file> |
Use existing bloat-scan report | Run new scan |
--auto-approve <level> |
Auto-approve: low, medium, none |
none |
--dry-run |
Preview all changes without executing | false |
--focus <area> |
Focus: code, docs, deps, or all |
all |
--backup-branch <name> |
Custom backup branch name | backup/unbloat-{date} |
--no-backup |
Skip backup branch creation | false |
Workflow Overview
- Scan/Load: Run integrated Tier 1 scan or load from
--from-scanreport - Prioritize: Group by type (DELETE, REFACTOR, CONSOLIDATE, ARCHIVE) and risk
- Backup: Create timestamped backup branch
- Remediate: Interactive approval for each finding with preview
- Verify: Run tests after each change, rollback on failure
- Summary: Report actions, token savings, rollback instructions
For remediation type definitions and risk assessment, see: @module:remediation-types
Interactive Prompts
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.
- 7d ago First seen · 210 lines · 27 tokens per session scan A b1a2e9f1c709
unbloat is a command published in the GitHub repository athola/claude-night-market (337 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 1,703 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 2026-09-03.
Other commands, from other repositories
bug-fix
Streamlines bug fixing by creating a GitHub issue first, then a feature branch for implementing and thoroughly testing the solution before merging.
fix-github-issue
Analyzes and fixes GitHub issues using a structured approach with GitHub CLI for issue details, implementing necessary code changes, running tests, and creating proper commit messages.
bug-fix
Streamlines bug fixing by creating a GitHub issue first, then a feature branch for implementing and thoroughly testing the solution before merging.
bug-detective
Systematic debugging assistant with troubleshooting steps.
code-review
Perform a comprehensive code review of recent changes.
CLAUDE
When debugging TUI commands like wt switch (interactive picker), use the tmux-cli skill (preferred) or MCP's node-terminal tools to test interactively.