A toolkit for monitoring and reducing wasted computing resources and context in Claude Code workflows. It includes checks and helpers for code bloat, context use, response size, and performance.

Use it to scan for bloat, audit AI-generated code, optimize context, filter logs, and review code quality.

It helps find unnecessary files, duplicated code, excessive context, and other sources of waste before they make coding work slower or more expensive.

conserve — Plugin for Claude Code by athola/claude-night-market

Install

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.

Clone the repo

git clone --depth 1 https://github.com/athola/claude-night-market

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/athola/claude-night-market/conserve/github.svg)](https://agentmods.dev/plugins/athola/claude-night-market/conserve)

Your own site

<a href="https://agentmods.dev/plugins/athola/claude-night-market/conserve"><img src="https://agentmods.dev/badge/plugins/athola/claude-night-market/conserve/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/athola/claude-night-market/conserve"><img src="https://agentmods.dev/badge/plugins/athola/claude-night-market/conserve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 15 skills, 6 commands, 5 agents cost 945 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

conserve 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 20d 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.

plugins/conserve/.claude-plugin/plugin.json · 59 lines

What it actually says

{
  "name": "conserve",
  "version": "1.9.21",
  "description": "Resource optimization and performance monitoring toolkit for efficient Claude Code workflows",
  "skills": [
    "./skills/action-first-output",
    "./skills/agent-expenditure",
    "./skills/bloat-detector",
    "./skills/clear-context",
    "./skills/code-quality-principles",
    "./skills/context-optimization",
    "./skills/cpu-gpu-performance",
    "./skills/decisive-action",
    "./skills/elegant-code",
    "./skills/mcp-code-execution",
    "./skills/response-compression",
    "./skills/token-conservation"
  ],
  "commands": [
    "./commands/ai-hygiene-audit.md",
    "./commands/bloat-scan.md",
    "./commands/elegant-code-review.md",
    "./commands/filter-log.md",
    "./commands/optimize-context.md",
    "./commands/unbloat.md"
  ],
  "agents": [
    "./agents/ai-hygiene-auditor.md",
    "./agents/bloat-auditor.md",
    "./agents/context-optimizer.md",
    "./agents/continuation-agent.md",
    "./agents/unbloat-remediator.md"
  ],
  "hooks": [],
  "keywords": [
    "conserve",
    "performance",
    "resource-management",
    "token-optimization",
    "context-optimization",
    "MECW",
    "efficiency",
    "bloat-detection",
    "dead-code",
    "code-cleanup",
    "technical-debt",
    "codebase-optimization",
    "elegant-code",
    "decision-ladder",
    "minimalism",
    "yagni"
  ],
  "author": {
    "name": "Alex Thola",
    "url": "https://github.com/athola"
  },
  "license": "MIT"
}

Contents

What it installs

The manifest is a name and a version. 15 skills, 6 commands, 5 agents travel with it, and installing the plugin installs all of them — 945 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

metadata.json 753 B

Changes

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.

20d ago Changed · -2 lines 3aea0b17407b
1mo ago Changed · -1 lines f8efee2bbb46
1mo ago First seen · 62 lines scan A a275d3e7e8df

Subscribe to this mod's changes

conserve is a plugin published in the GitHub repository athola/claude-night-market (343 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Claude Code Debugging Productivity awesome-claude-code awesome-claude-skills claude-code-plugins-marketplace claude-commands claude-hooks

lark

A plugin for operating Feishu/Lark workplace services such as messages, documents, spreadsheets, calendars, files, tasks, and meetings through a local command-line tool.

DropFan/claude-code-plugins · not measured

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.

xbim08/awesome-claude-code-plugins · not measured

debugger

Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.

xbim08/awesome-claude-code-plugins · not measured

open-kioku

Your coding agent shows its evidence before it edits, and its diff is verified against the plan it declared. A local, read-only MCP server with 16 tools: code and regex search, symbol definitions and references, dependency paths, impact analysis, context packs, planchange and verifychange, from an index under the rep.

shivyadavus/open-kioku · not measured

humanizer

Rewrite AI-sounding text so it reads like the writer without changing what it says.

blader/humanizer · not measured

claude-plugins-official marketplace

Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.

anthropics/claude-plugins-official · not measured