Draft spec-backed RFI responses, stamp submittals with the firm's Bluebeam review stamps and comment block, and log the responses you accept to the EPLUS knowledge base.
3 skills · 1 agent · hooks
0
claude
EPLUS Model Routing
Cost control: detects when a session runs on Opus or Fable, injects the routing rule at that moment, and ships sonnet-standard and haiku-fast workers to delegate to. Expensive spawns need an explicit click.
/
Plugin eplus-model-routing from marketplace eplus-claude-plugins in Engineering-PLUS/eplus-plugin-catalog. Commands read from the repo's manifest — 3 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 (1)
model-routingUse whenever the "Model:" line in your env block names Opus or Fable, whenever a [model-routing] note appears in context, before any multi-step task, and whenever the user asks about models, speed, or cost. Teaches an expensive main thread to keep itself to decisions and hand the work to the sonnet-
Subagents (2)
haiku-fastThe cheapest worker (Haiku 4.5, well under Sonnet per token, 128K context; the cost table lives in the model-routing skill). Route mechanical work here from an Opus or Fable main thread - reformatting, extraction of fields from text, classification and tagging, list cleanup, renaming, simple transfo
sonnet-standardThe standard worker (Sonnet 5, a fraction of Opus or Fable per token; the cost table lives in the model-routing skill). Route the BULK of real work here from an Opus or Fable main thread - research, reading and summarizing documents, drafting emails, memos, summaries and report text, analysis, codin
Hooks (3)
- SessionStart
& "${CLAUDE_PLUGIN_ROOT}\scripts\note-model.ps1"
- UserPromptSubmit
& "${CLAUDE_PLUGIN_ROOT}\scripts\route-check.ps1"
- PreToolUse
& "${CLAUDE_PLUGIN_ROOT}\scripts\spawn-gate.ps1"
More from Engineering-PLUS/eplus-plugin-catalog
All 5 plugins →EPLUS branding (default fonts) skill, a workflow-packager skill that turns document-heavy conversations into reusable skills, and the eplus-getting-started onboarding tour — required install for the Claude desktop fleet
4 skills
0
EPLUS Punch Reports
claudeDraft punch reports end to end from a PlanGrid pull with /punch-report, and search four years of EPLUS punch walks for precedent, recurring deficiencies, and the evidence photos behind them.
3 skills
0
EPLUS Error Reporting
claudeFire-and-forget issue logging — when an EPLUS tool fails or you ask for an EPLUS-side change, the model files a report to the central log for the team to review.
1 skill · hooks
0
Similar plugins
ruflo-cost-tracker
claudeToken usage tracking, model cost attribution per agent, budget alerts, and optimization recommendations
24 skills · 1 command · 1 agent · hooks
ruvnet/ruflo 81,589
headroom-skill
claudeSkill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.
1 skill
headroomlabs-ai/headroom 79,508
ppt-master
claudeGenerate natively editable PPTX from PDF / DOCX / URL / Markdown — real DrawingML shapes, text boxes, charts, and animations. Note: run `pip install -r requirements.txt` inside the installed plugin directory for the Python post-processing scripts to work.
1 skill
hugohe3/ppt-master 76,375
Install the "AAS Documents & Presentations" workflow plugin from Agentic Awesome Skills.
7 skills
sickn33/agentic-awesome-skills 49,620
azure
claudeTransform 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
ifixai
claudecodexIndependent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).
1 skill · hooks
ifixai-ai/iFixAi 45,158
Maintain EPLUS Model Routing?
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 plugins5 plugins