claude

conserve

Context optimization, bloat detection, CPU/GPU monitoring, and token conservation for efficient Claude Code sessions

350 on GitHubby Alex Tholav1.10.1MITupdated 6 days ago
/

Plugin conserve from marketplace claude-night-market in athola/claude-night-market. Commands read from the repo's manifest — 6 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (12)

  • action-first-output

    Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.

  • agent-expenditure

    Tracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficiency or after a multi-agent run.

  • bloat-detector

    Detects codebase bloat via dead code, duplication, complexity, and doc bloat scans. Use when codebase feels large or before a release.

  • clear-context

    Manages context overflow by handing off to a fresh subagent at 80% usage. Use when context pressure is critical and work must continue uninterrupted.

  • code-quality-principles

    Applies KISS, YAGNI, and SOLID principles for clean code with reduced complexity. Use when refactoring or reviewing code for over-engineering.

  • context-optimization

    Optimizes context window via MECW principles and memory tiering. Use when context exceeds 30% or before long multi-step tasks.

  • cpu-gpu-performance

    Establishes CPU/GPU baselines before resource-intensive operations. Use before builds, training runs, or any task that pins cores or GPUs for over a minute.

  • decisive-action

    Guides when to ask clarifying questions versus proceed autonomously. Use to reduce unnecessary clarifying questions when intent is clear.

  • elegant-code

    Guide minimal code via a decision ladder with full safety, edge, and negative-case coverage. Use when adding code, choosing a dependency, or auditing a diff.

  • mcp-code-execution

    Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

  • response-compression

    Compresses verbose responses by removing filler and framing to save 200-400 tokens. Use when responses feel bloated or context is filling fast.

  • token-conservation

    Enforces token quota management at session start with conservation and compression checks. Use at the start of every session or before large context loads.

Slash commands (6)

  • /conserve:ai-hygiene-audit

    Audit codebase for AI-generated code quality issues (vibe coding, Tab bloat, slop)

  • /conserve:bloat-scan

    Scan for codebase bloat using 3-tier progressive analysis: dead code, duplication, God classes, and documentation waste.

  • /conserve:elegant-code-review

    Review the current working diff against the elegant-code decision ladder and propose deletions, honoring the negligence floor.

  • /conserve:filter-log

    Suggest tier-1 filter commands for a log file before any compression or paste. Anchors on the log-debugging-hygiene module.

  • /conserve:optimize-context

    Analyze context window usage against MECW principles and recommend reductions

  • /conserve:unbloat

    Remove dead code, duplicate files, and unused dependencies with user approval at each step. Backs up before deleting.

Subagents (5)

  • ai-hygiene-auditor

    Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor. to: opus hints: - large_codebase_over_50k - ambiguous_ai_vs_human_patterns - complex_refactoring_recommendations - con

  • bloat-auditor

    Execute progressive bloat detection scans (Tier 1-3), generate prioritized reports, and recommend cleanup actions. to: opus hints: - complex_codebase - ambiguous_findings - high_risk_deletions - context: User requests bloat scan user: "Run a bloat scan to find dead code" assistant: "I'll perform a T

  • context-optimizer

    Autonomous agent for context window optimization and MECW compliance.

  • continuation-agent

    Lightweight agent designed to continue work from a session state checkpoint. Spawned when the parent agent exceeds context thresholds. This agent: 1. Reads the session state file 2. Re-establishes necessary context 3. Continues the task without interruption 4. Can spawn another continuation agent if

  • unbloat-remediator

    Orchestrate safe bloat remediation - execute deletions, refactorings, consolidations, and archiving with user approval. Creates backups, runs tests, provides rollback. to: opus hints: - complex_refactoring - high_risk_changes - core_infrastructure - many_cross_file_dependencies - context: User reque

Hooks (8)

  • Setup

    "${CLAUDE_PLUGIN_ROOT}/hooks/setup.sh"

  • PermissionRequest

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/permission_request.py"

  • PreToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/context_warning.py"

  • PostToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/tool_output_summarizer.py"

  • PreCompact

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/pre_compact_preserve.py"

  • PermissionDenied

    "${CLAUDE_PLUGIN_ROOT}/hooks/permission_denied_logger.py"

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh"

  • Notification

    "${CLAUDE_PLUGIN_ROOT}/hooks/background_agent_notice.py"

View source on GitHub athola.github.io

More from athola/claude-night-market

All 23 plugins →

sanctum

claude

Git workflows: commit messages, PR preparation, documentation updates, version management, sessions, and deferred-item capture

18 skills · 49 commands · 9 agents · hooks

350

abstract

claude

Skill authoring, hook development, evaluation frameworks, and escalation governance for the Claude Code plugin ecosystem

14 skills · 17 commands · 6 agents · hooks

350

pensive

claude

Multi-discipline code review: architecture, bugs, APIs, blast radius analysis, security, tests, Makefiles, and NASA Power of 10 analysis

15 skills · 14 commands · 6 agents · hooks

350

leyline

claude

Foundation infrastructure: auth flows, quota management, error patterns, markdown formatting, trust verification, and injection detection

25 skills · 3 commands · hooks

350

attune

claude

Full-cycle project development: brainstorm, specify, plan, initialize, execute, and polish with war-room deliberation for strategic decisions

14 skills · 11 commands · 2 agents

350

scribe

claude

Documentation review, cleanup, and generation with AI slop detection, style learning, and human-quality writing enforcement

11 skills · 9 commands · 5 agents

350

Similar plugins

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

Token usage tracking, model cost attribution per agent, budget alerts, and optimization recommendations

24 skills · 1 command · 1 agent · hooks

ruvnet/ruflo 81,589

Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer

8 skills · 1 MCP server

ChromeDevTools/chrome-devtools-mcp 55,181

Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.

2 commands

alibaba/open-code-review 50,068

azure

claude

Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform real-world tasks: listing resources, validating deployments, diagnosing infrastructure issues, and optimizing costs across 50+ Azure services.

44 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

Cloud architecture design for AWS/Azure/GCP/OCI, Kubernetes cluster configuration, Terraform infrastructure-as-code, hybrid cloud networking, and multi-cloud cost optimization

8 skills · 7 agents

wshobson/agents 42,461

Maintain conserve?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins23 plugins