glimmer-delegation

glimmer-delegation is a skill for Claude Code from athola/claude-night-market. It costs 36 tokens per session (1,082 once invoked), scanned C, original, MIT.

A delegation adapter for Muse Glimmer, a 30-billion-parameter AI model running locally through Ollama. It keeps the prompt on the machine instead of sending it to a network service.

In plain words
What is it for?
Use it for delegated coding or analysis that cannot leave the machine, after the local Glimmer model has been installed.
Why use it?
It provides a local option when online providers are unavailable or the task must stay private. The trade-off is that it may be slower and less capable than network-based providers.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python scripts/delegation_executor.py glimmer "Summarize" \.

Part of the conjure plugin — 11 skills shipped together

Good fit Use it for delegated coding or analysis that cannot leave the machine, after the local Glimmer model has been installed.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/athola/claude-night-market
agentmods
npx agentmods add skills/athola/claude-night-market/glimmer-delegation

Made for: Claude Code.

Or install conjure, the plugin that ships this one along with the rest of its 11 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 glimmer-delegation

README.md
[![agentmods](https://agentmods.dev/badge/skills/athola/claude-night-market/glimmer-delegation/github.svg)](https://agentmods.dev/skills/athola/claude-night-market/glimmer-delegation)
Your own site
<a href="https://agentmods.dev/skills/athola/claude-night-market/glimmer-delegation"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/glimmer-delegation/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for glimmer-delegation

Your own site · 80×15
<a href="https://agentmods.dev/skills/athola/claude-night-market/glimmer-delegation"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/glimmer-delegation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,082 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00036 $0.01082
Opus 5 $0.00018 $0.00541
Sonnet 5 $0.00007 $0.00216
Haiku 4.5 $0.00004 $0.00108

Measured 9d ago against content hash bd469eacadae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

glimmer-delegation scanned grade C with 2 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 9d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://ollama.com/install.sh | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://ollama.com/install.sh | sh
plugins/conjure/skills/glimmer-delegation/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Table of Contents

Glimmer Delegation

Overview

Glimmer is Meta's Muse Glimmer served locally through ollama, so a delegation to it spends no quota and sends no prompt off the machine. It is the last entry in the candidate order for the same reason it is the safe one: a local 30B model is slower and weaker than any of the network providers ahead of it.

When To Use

  • delegation-core selected glimmer for the task
  • Every network provider is exhausted and the work still has to happen
  • The prompt must not leave the machine, whatever the cost in quality

When NOT To Use

  • The task needs the strongest available model. Glimmer is the floor, not a peer of the network providers
  • ollama list shows no muse-glimmer:30b. A registered provider whose model was never pulled fails at the first delegation, not at registration

Prerequisites

Installation

curl -fsSL https://ollama.com/install.sh | sh
ollama pull muse-glimmer:30b

Both steps are required. Installing ollama registers the binary and pulls nothing, so ollama --version answering is not evidence that a delegation will succeed.

Authentication

None. auth_method is "none" and the auth probe is empty, because a local server has no credential to check.

Quick Start

Using the shared delegation executor

uv run python scripts/delegation_executor.py glimmer "Summarize" \
  --files src/

Through the Makefile

make -C plugins/conjure delegate-glimmer PROMPT='Summarize' FILES='src/'

Direct CLI usage

ollama run muse-glimmer:30b "Explain this module"

Smart Delegation

glimmer carries priority=80, the highest number in the registry, which places it last in the candidate order. It declares no model ids, because the model is fixed by the subcommand rather than chosen per call.

Read the full file on GitHub · 144 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. 9d ago First seen · 144 lines · 36 tokens per session scan C bd469eacadae

Subscribe to this mod's changes

glimmer-delegation is a skill published in the GitHub repository athola/claude-night-market (337 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 1,082 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

claude_code_delegation

Delegate coding, review, and refactor tasks to Claude Code CLI through Row-Bot's approval-gated shell workflow.

siddsachar/row-bot · 31 tokens

local-llm-tool

Local LLM execution tool for text generation and chat through Ollama or vLLM endpoints. Use when: running on-prem inference, calling a local GPU model, or summarizing with a self-hosted LLM.

xuiltul/animaworks · 50 tokens

local-llm-ops

Local LLM operations with Ollama on Apple Silicon, including setup, model pulls, chat launchers, benchmarks, and diagnostics.

bobmatnyc/claude-mpm-skills · 33 tokens

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…

shajith003/awesome-claude-skills · 62 tokens

slack-gif-creator

Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".

shajith003/awesome-claude-skills · 57 tokens

canvas-design

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

shajith003/awesome-claude-skills · 59 tokens