agentmods.dev

simba-optimizer-runs

simba-optimizer-runs is a skill for Claude Code, Codex from getsimba-ai/simba-mcp. It costs 65 tokens per session (679 once invoked), scanned A, original, MIT.

Instructions for running Simba budget optimization models, which recommend how to divide an advertising budget across channels and time periods.

In plain words
What is it for?
Use it to set channel budget limits, spending schedules, cost-per-thousand-impression values, revenue or profit objectives, and to poll and interpret completed optimization runs.
Why use it?
They prevent incorrectly formatted inputs and help interpret whether results are based on expected revenue, profit, or more cautious assumptions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 0repo 12d ago A scan 65 tokens original MIT

Good fit Use it to set channel budget limits, spending schedules, cost-per-thousand-impression values, revenue or profit objectives, and to poll and interpret completed optimization runs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/getsimba-ai/simba-mcp/simba-optimizer-runs
View source ↗ getsimba-ai/simba-mcp getsimba.ai
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.

Any agent
npx skills add getsimba-ai/simba-mcp --skill simba-optimizer-runs
Clone the repo
git clone --depth 1 https://github.com/getsimba-ai/simba-mcp

Made for: Claude Code, Codex.

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.

agentmods badge for simba-optimizer-runs

README.md
[![agentmods](https://agentmods.dev/badge/skills/getsimba-ai/simba-mcp/simba-optimizer-runs.svg)](https://agentmods.dev/skills/getsimba-ai/simba-mcp/simba-optimizer-runs)
Your own site
<a href="https://agentmods.dev/skills/getsimba-ai/simba-mcp/simba-optimizer-runs"><img src="https://agentmods.dev/badge/skills/getsimba-ai/simba-mcp/simba-optimizer-runs.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 679 The whole file, excluding the scripts and references it only reads on demand.
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.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.00679
Opus 5 $0.00032 $0.00340
Sonnet 5 $0.00013 $0.00136
Haiku 4.5 $0.00006 $0.00068

Measured 7d ago against content hash f9291d34f2c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

simba-optimizer-runs 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 7d 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.

skills/simba-optimizer-runs/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Simba optimizer runs

Payload rules (the four that reject or mislead)

  1. Channel keys = ACTIVITY-COLUMN names, case- and space-sensitive. Get them from channel_summary or get_scenario_template (avg_cpu_by_channel doubles as baseline CPM).
  2. bounds are PERCENTAGES of total_budget (0–100), not currency.
  3. laydown_weights and period_cpm are ARRAYS of length num_periods ({"TV": [10, 10, 10, 10]}, never {"TV": 10}); CPMs strictly positive; the same channel keys must appear in bounds, laydown_weights, AND period_cpm.
  4. gamma is uncertainty aversion (objective = mean − gamma·spread): 0 = maximize expected return; higher = more conservative. Typical dashboard range 0–0.1.

Objectives and margin

  • objective="profit" needs a margin: the model's stored operating margin is used automatically; otherwise pass forward_margin or the API errors. Result Revenue/ROI columns are then on the profit basis.
  • group_bounds (joint % constraints over channel sets) forces the slsqp engine; a BINDING group's members legitimately sit off the global marginal.

Poll and read

  • run_optimizer returns 202 + a run_id ("opt_..."). Poll get_optimizer_results(model_hash, run_id=...) — the model-level form reflects only the LATEST run and a newer run overwrites it.
  • Column conventions must not be mixed in one summary:
    • Revenue/ROI = the solver's decision math (removal-lift counterfactual).
    • OptimizedEvalRevenue/ROI, HistoricalRevenue/ROI = fitted-convention comparison columns (match the Contributions panel).
    • ObjectiveMarginal (solver's equalized marginal) ≠ MroiAtOptimized (posterior mROI at the optimized spend, with 94% HDI) — they can differ by several times; quote the one matching the question.

Run history and curation

  • list_runs(artifact="optimizer"|"scenario", ...): pinned-first then newest-first. count is the PAGE length, not the total — page until a short page. The objective is NOT in summaries: fetch the run's inputs (profit runs carry objective: "profit"; revenue runs omit the key).
  • update_run renames/annotates (sets auto_named false permanently); set_run_pinned pins declaratively and idempotently. Scenario runs work the same via get_scenario_results(run_id=...).

Read the full file on GitHub · 54 lines

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.

  1. 7d ago First seen · 54 lines · 65 tokens per session scan A f9291d34f2c2

Subscribe to this mod's changes

simba-optimizer-runs is a skill published in the GitHub repository getsimba-ai/simba-mcp (0 stars, last pushed 12d ago), licensed MIT. It adds 65 tokens to every session and 679 once invoked, about $0.0003 per session on Opus 5. 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 2026-08-31.

Analytics and metricsMarketing and SEObayesianclaudemarketing-mix-modelingmcpmmmmodel-context-protocol
Related

Other skills, from other repositories

mmm-api-reference

Exact pymc-marketing API reference for MMM code, verified against v1.1.0. Use when writing or reviewing pymc-marketing code, checking constructor signatures, method names, return types, import paths, or plotting/evaluation/optimisation calls. Also use when migrating 0.x code to 1.x, debugging ImportError or…

Yakoub-ai/agent-mmm · 96 tokens

mmm-channel-semantics

How each type of marketing channel should be represented in an MMM — its role (paid media, reach-and-frequency, organic, non-media treatment, control), whether it is driven by spend or exposure, its carryover and saturation behaviour, and whether a ROAS is even defined for it. Use when deciding what a column means…

Yakoub-ai/agent-mmm · 112 tokens

mmm-meridian

Google Meridian reference and practice guide, verified against google-meridian 1.8.0. Use when building, reviewing or debugging a Meridian model, wiring InputData and CoordToColumns, setting ROI/mROI/contribution priors, configuring knots and adstock/saturation specs, handling reach-and-frequency channels, running the…

Yakoub-ai/agent-mmm · 85 tokens

mmm-model-building

Constructing an MMM with pymc-marketing 1.x — model architecture, adstock and saturation choice, prior specification, likelihood and link function, seasonality and trend, panel dimensions, and the fitting strategy. Use when building a new model, choosing transformations, writing modelconfig, setting priors from…

Yakoub-ai/agent-mmm · 87 tokens

mmm-attribution

Turning a fitted MMM into channel contributions, ROAS, CPA, marginal returns and response curves — correctly. Use when extracting contributions, computing return metrics with uncertainty, reading saturation curves, decomposing the target, comparing efficiency across channels, or diagnosing an implausible attribution…

Yakoub-ai/agent-mmm · 81 tokens

mmm-baseline-and-trend

The baseline of an MMM — intercept, trend, seasonality and controls — and how it competes with media for variance. Use when the baseline is negative, implausibly large or small, when deciding between a fixed intercept, a linear trend, changepoints, knots or a time-varying intercept, when seasonality is absorbing…

Yakoub-ai/agent-mmm · 100 tokens