By ai-scm
Token-saving hooks and skills: log-filter (80-92%), read-once (40-80%), session-context best practices, plus token-audit, opusplan, rtk-setup, context-diet, session-hygiene, bld-onboard, token-scan, and git-commit skills.
Full onboarding for bld-token-cost-efficiency plugin. Use when user says "/bld-onboard", "setup plugin", "configure efficiency plugin", "first time setup", or just installed the plugin.
Analyze and optimize Claude Code context window usage. Use when user says "/context-diet", "optimize context", "context too large", "reduce context", "context usage", or asks about context window optimization.
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
Hybrid planning workflow: use Opus for architecture/planning, then Sonnet for execution. Use when user says "/opusplan", "plan con Opus", or needs architectural decisions before coding.
Install and configure RTK (Rust Token Killer) for Claude Code. Use when user says "/rtk-setup", "install rtk", "configure rtk", "setup rtk", or asks how to install RTK.
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Blend's Claude Code plugin marketplace. Curated tools for token efficiency, developer productivity, and standardized workflows.
Security note: Plugins execute code on your machine with your user privileges. Only install plugins from sources you trust.
# Add the marketplace
/plugin marketplace add ai-scm/bld-claude-plugins
# Install a plugin
/plugin install bld-token-cost-efficiency@bld-claude-plugins
# Run onboarding
/bld-onboard
v1.2.0Reduce Claude Code token consumption by 60-90% through automated output filtering, session caching, and optimized workflows.
3 hooks | 8 skills | Category: productivity
| Component | Type | Description |
|---|---|---|
log-filter | Hook (PreToolUse) | Filters verbose test/build/lint output before reaching context. 80-92% savings. |
read-once | Hook (PreToolUse) | Blocks redundant re-reads of unchanged files (>1KB) per session. 40-80% savings. |
session-context | Hook (SessionStart) | Injects token best practices + RTK installation nudge. |
/bld-onboard | Skill | Full onboarding: dependencies, tools, analysis, verification. |
/token-audit | Skill | Session token usage and savings snapshot. |
/token-scan | Skill | Repository config audit with A-F report card. |
/context-diet | Skill | Analyze and optimize context window consumption. |
/session-hygiene | Skill | Session health check: cache, RTK, deps, model recommendation. |
/opusplan | Skill | Hybrid Opus (planning) + Sonnet (execution) workflow. |
/rtk-setup | Skill | Install and configure RTK (Rust Token Killer). |
/git-commit | Skill | Conventional Commits with intelligent staging and safety protocol. |
/plugin marketplace add ai-scm/bld-claude-plugins
Then browse and install with /plugin.
Add to your project's .claude/settings.json so team members get prompted automatically:
{
"extraKnownMarketplaces": {
"bld-claude-plugins": {
"source": {
"source": "github",
"repo": "ai-scm/bld-claude-plugins"
}
}
}
}
Optionally auto-enable specific plugins:
{
"enabledPlugins": {
"bld-token-cost-efficiency@bld-claude-plugins": true
}
}
In Claude.ai > Admin Settings > Claude Code > Managed Settings, add the same extraKnownMarketplaces JSON. All org members receive the marketplace automatically.
Want to contribute a plugin to this marketplace? See CONTRIBUTING.md for the complete guide.
Quick overview:
plugins/
your-plugin-name/
.claude-plugin/
plugin.json # Plugin manifest (required)
hooks/
hooks.json # Hook registration (optional)
your-hook.sh # Hook scripts
skills/
your-skill/
SKILL.md # Skill definition (optional)
README.md # Plugin documentation (required)
| Dependency | Required | Purpose | Install |
|---|---|---|---|
jq | Yes (for hooks) | JSON parsing in hook scripts | apt install jq / brew install jq |
rtk | Optional | Token-optimized CLI proxy (60-90% savings) | /rtk-setup or rtk-ai/rtk |
python3 | Optional | Enhanced plugin analytics | Usually pre-installed |
bld-claude-plugins/
.claude-plugin/
marketplace.json # Marketplace catalog (lists all plugins)
plugins/
bld-token-cost-efficiency/
.claude-plugin/
plugin.json # Plugin manifest
hooks/ # Auto-discovered by Claude Code
skills/ # Auto-discovered by Claude Code
README.md
CONTRIBUTING.md # Guide for plugin authors
LICENSE
README.md # This file
MIT - See LICENSE for details.
Individual plugins may have their own licenses specified in their plugin.json.
npx claudepluginhub ai-scm/bld-claude-plugins --plugin bld-token-cost-efficiencyMinimize token waste in all bash, file, and data processing operations
Resource optimization and performance monitoring toolkit for efficient Claude Code workflows
Claude Code context optimizer. Builds a local static repo graph, injects ranked file:line candidates through a UserPromptSubmit hook, and adds a SessionStart prewarm brief. No embeddings, no server, no telemetry. Measured live A/B: 40.9% aggregate token reduction across 36 Claude Code calls. v2.10 structural slicing: a PreToolUse hook intercepts whole-file reads and hands Claude the file's outline (symbols + exact line ranges from the graph) so it reads the 40 lines it needs, not 800 that get re-sent every turn. Receipts (/savings) measure both sources — searches avoided and big reads sliced — causally from your transcript.
Opus 4.8-aware context optimization: silent-by-default hooks, honest NET token savings, big-file map-then-load, Context Control Center, per-task tracking, prompt coach
Estimate per-turn token cost of your .claude/ configuration and CLAUDE.md. Always-loaded vs path-scoped vs invoked-only, with top contributors. Use --api for exact counts via Anthropic's count_tokens endpoint.
45% cost reduction measured. Cache expiry prevention, SubTask auto-delegation, zero-cost context restoration, real-time cost dashboard. The only Claude Code plugin built from CC source analysis.