Model-selection economist agent for Claude Code: decides which Claude model (and effort/token budget) each task in a flow should run on by weighing effectiveness need against efficiency pressure and difficulty, bookended around a build as a right-sizing blueprint and a closing usage report -- with token_ceiling itself computed deterministically from six rated real-work signals, not free-handed. Ships with eleven companion skills: installing the standing before/after mandate in a target repo, previewing the routing map for an intent without building anything, retroactively auditing every real model call already shipped in a target repo, prescribing a minimal output schema for one agent's handoff to its controller, guarding token budgets and the routing-map status ledger while work is in flight, validating candidate real-work signals and studying/tuning the agent's research-grounded layers, and publishing dated release/research reports.
Plugin model-right-sizer from marketplace cloudzero in Cloudzero/cloudzero-claude-marketplace. Commands read from the repo's manifest — 30 days ago.
model-right-sizer-auditOne-shot, PER-CALL-SITE audit of a repo's EXISTING LLM calls — every place code invokes a model (an SDK/API call, a sub-agent dispatch, an agent frontmatter definition), decomposed by INTENT into the distinct jobs it does, never a grep hit on a model name and never one candidate per file. A skill pi
model-right-sizer-budget-guardThe while-work-is-in-flight companion to `model-right-sizer-dryrun`: once `work_routing_map[]` is real and being dispatched as sub-agents, the runbook for keeping two things honest — the status ledger (`status`/`status_updated_at`/`status_note` per row, flipped at every real transition) and the toke
model-right-sizer-dryrunPreview the model-routing MAP for an intent without building anything. You give it a free-text INTENT — "build a CLI that…", "add a feature that…", "refactor X into Y" — and it invokes the `model-right-sizer` agent in BLUEPRINT-ONLY mode: decompose the work, score each piece, and emit a single schem
model-right-sizer-holdout-tuningTune model-right-sizer's wording knobs (`eval/tuning/knobs.py`) against a REAL, already-measured build's actual token spend — not the synthetic benchmark `model-right-sizer-prompt-tuning` searches, nor a fresh build per candidate. Picks a task from `overfitting_guard.py`'s `HOLDOUT_TASKS` registry (
model-right-sizer-installStamp a model-right-sizer mandate onto the CURRENT repo's agent-instructions file — `CLAUDE.md`, `AGENTS.md`, or both, whichever the repo has. Idempotent and append-only: an existing file is never overwritten, only the marker-delimited mandate block is inserted or refreshed. The mandate's "before" h
model-right-sizer-layer-ablationEmpirically measure what each of model-right-sizer's four research-grounded citation layers (Token Economics, IBPO, BudgetThinker, Speculative Decoding) actually does to its blueprints — instead of trusting the citations alone. Renders layer-ablated variants (any of the 16 layer subsets), runs a fix
model-right-sizer-prompt-tuningTune the exact WORDING of model-right-sizer's four already-shipped research-grounded layers to maximize real-execution accuracy (effort stayed within budget, per `classify_budget_adherence`) — not whether to include a layer (see `model-right-sizer-layer-ablation`), but how an included layer should b
model-right-sizer-release-reportPublish a per-version release report for `eval/token_ceiling_formula.py` every time `FORMULA_VERSION` bumps — the exact configuration (formula, signal weights, calibration constants), a ranked gap list for the next contributor, and what's settled and not worth re-relitigating. Why this is its own sk
model-right-sizer-research-reportPackage up every result this plugin's tuning/validation research has produced — the layer-ablation study, the prompt-tuning coordinate-ascent passes and the dispatch-floor-awareness/held-out-task work, the averaged-vs-additive `token_ceiling_formula.py` pivot, and the real-work-signal validation exp
model-right-sizer-schemaPrescribe a minimal output schema for ONE agent's handoff to its controller — the `model-right-sizer` agent's "Agent-to-agent message-schema design" lever, scoped to a single seam instead of a whole flow's blueprint. Given a target agent (a path to an existing agent `.md` file, or a description of o
model-right-sizer-signal-validationTest whether a candidate real-work signal in `eval/token_ceiling_formula.py` (e.g. `context_ingestion_volume`, `investigative_uncertainty`, or new) deserves a nonzero default weight, via the blind multi-draw rating + correlation methodology this repo's research converged on. Ratings must come from g
model-right-sizerModel-selection economist — decides which Claude model each task in a flow should run on, independent of load, by weighing EFFECTIVENESS (capability the outcome needs) against EFFICIENCY (cost, latency, volume) and recommending the SMALLEST model that clears the bar. Grounds every call in live model
Comprehensive CloudZero cost analysis plugin providing AI-powered skills for investigating cost spikes, analyzing trends, comparing spending, optimizing services, optimization triage, projecting infrastructure costs from code diffs and IaC definitions, and tracking cloud infrastructure costs using CloudZero's MCP server
12 skills · 1 MCP server
MetaHarness integration — surfaces score/genome/mint/mcp-scan/threat-model via skills; pairs with @metaharness/router (ADR-148/149) for cost-optimal model routing; honors ADR-150 optional-augmentation constraint
13 skills · 1 command · 1 agent · hooks
Build, deploy, and operate applications on AWS. Skills to author infrastructure-as-code, use core services, and complete common tasks.
27 skills · 1 MCP server
Cut LLM API spend via model routing, prompt caching, prompt compression, and per-feature cost observability. Use when AI costs are too high, choosing between models, or launching an AI feature without cost architecture. NOT for RAG design or prompt quality (separate skills).
1 skill
Per-stage model routing + pre-flight cost gate for Claude Code ultracode dynamic workflows. Pins an explicit model + effort on every agent() subagent stage, estimates cost before launch, and ships a static guard + PreToolUse gate that flag stages which would silently inherit the session's Opus model. Zero dependencies, no telemetry, MIT.
1 skill · 12 commands · hooks
Build, deploy, and operate applications on AWS. Skills to author infrastructure-as-code (CDK, CloudFormation), use core services (Lambda, API Gateway, Step Functions, ECS/Fargate, ECR, IAM, Amazon Bedrock with Knowledge Bases and Guardrails, AWS Blocks), select and operate databases across relational, key-value, document, wide-column, graph, time-series, and in-memory engines (Aurora PostgreSQL/MySQL, Aurora DSQL, RDS, Oracle Database@AWS, DynamoDB, DocumentDB, Keyspaces, Neptune, Timestream, ElastiCache, and MemoryDB), and complete common tasks across observability (CloudWatch, X-Ray, CloudTrail, ADOT), messaging and streaming (SQS, SNS, EventBridge, Kinesis, MSK), AWS SDKs (boto3, JS v3, Swift), cost optimization, and Well-Architected Framework reviews across all six pillars.
27 skills · 1 MCP server
AKS operational skills for troubleshooting, advanced cost-efficiency analysis, known issues, GPU inference, and packet capture.
6 skills
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.