roster-refresh

roster-refresh is a skill for Claude Code from Bumblebiber/its-over-9k. It costs 68 tokens per session (478 once invoked), scanned A, original, MIT.

A skill that refreshes model scores and prices from OpenRouter, a service that provides information about AI models and their costs. It can propose or apply updates to model chains when the score improves without increasing blended cost.

In plain words
What is it for?
Use it weekly, after major model releases, or when asked to refresh the roster; it supports fixture-based offline checks and live or manual update modes.
Why use it?
It keeps a model-selection matrix based on current evidence and applies stated update rules instead of relying on outdated values.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions OpenCode.

Part of the o9k-roster plugin — 2 skills shipped together

Good fit Use it weekly, after major model releases, or when asked to refresh the roster; it supports fixture-based offline checks and live or manual update modes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bumblebiber/its-over-9k/roster-refresh
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 Bumblebiber/its-over-9k --skill roster-refresh
Clone the repo
git clone --depth 1 https://github.com/Bumblebiber/its-over-9k

Made for: Claude Code.

Or install o9k-roster, the plugin that ships this one along with the rest of its 2 skills.

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 roster-refresh

README.md
[![agentmods](https://agentmods.dev/badge/skills/bumblebiber/its-over-9k/roster-refresh.svg)](https://agentmods.dev/skills/bumblebiber/its-over-9k/roster-refresh)
Your own site
<a href="https://agentmods.dev/skills/bumblebiber/its-over-9k/roster-refresh"><img src="https://agentmods.dev/badge/skills/bumblebiber/its-over-9k/roster-refresh.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 478 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 $0.00068 $0.00478
Opus 5 $0.00034 $0.00239
Sonnet 5 $0.00014 $0.00096
Haiku 4.5 $0.00007 $0.00048

Measured 7d ago against content hash 7515370a3214, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

roster-refresh 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.

plugins/o9k-roster/skills/roster-refresh/SKILL.md · 47 lines

What it actually says

roster-refresh — Keep the Matrix Current

Scores and prices are evidence; chains stay deterministic. Never invent rankings in prose — run the collector.

ROSTER="node <marketplace>/plugins/o9k-roster/scripts/roster.mjs"

Requires OPENROUTER_API_KEY for live fetch. Offline smoke:

$ROSTER refresh --fixture-dir <marketplace>/plugins/o9k-roster/scripts/collectors/fixtures
$ROSTER refresh --fixture-dir ... --apply

Live refresh (normal)

  1. Ensure OPENROUTER_API_KEY is set.
  2. $ROSTER refresh — writes ~/.o9k/roster-scores.json, prints propose report.
  3. $ROSTER refresh --apply — semiauto: auto-rewrites role chain heads when score ≥ current + min_delta (default 2) AND blended cost does not rise. Backs up roster.json first. pin_head: true on a role → skip.
  4. Show the user the APPLY vs SKIP sections verbatim.
  5. Hosted open-weight models (Hermes/OpenCode) are included; local Ollama is not.

Manual-only

$ROSTER propose — report without writing. $ROSTER apply-scores — apply gates using the last scores file (no re-fetch).

Cron

Live trigger: system crontab 0 10 * * 1~/.hermes/scripts/roster-refresh-wrapper.sh (Hermes gateway often down; same pattern as TIM watchdogs).

Hermes job id e0c56515831c exists but is paused (avoids double-fire). Reports: ~/.hermes/cron-outputs/roster-refresh/.

Manual: bash ~/.hermes/scripts/roster-refresh-wrapper.sh

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 · 47 lines · 68 tokens per session scan A 7515370a3214

Subscribe to this mod's changes

roster-refresh is a skill published in the GitHub repository Bumblebiber/its-over-9k (0 stars, last pushed 10d ago), licensed MIT. It adds 68 tokens to every session and 478 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.

Related

Other skills, from other repositories

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens