Agent skill

Glimmer Delegation

by athola in athola/claude-night-market

Delegates tasks to a locally served Muse Glimmer via ollama.

MITAuto-check: notesAI & LLM Engineering

Install Glimmer Delegation

skills CLI
$ npx skills add athola/claude-night-market --skill glimmer-delegation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install athola/claude-night-market glimmer-delegation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/conjure/skills/glimmer-delegation .claude/skills/glimmer-delegation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
glimmer-delegation
GitHub stars
341
Token cost
~988 tokens
SKILL.md length
440 words
Files
1
Skills in repo
152
Repo updated
First seen
Licence
MIT

At a glance

Delegates tasks to a locally served Muse Glimmer via ollama.

  • Delegation-core selects glimmer
  • SKILL.md covers Overview, When To Use, When NOT To Use and Prerequisites, plus 4 more sections
  • Calls ollama, curl and sh; reaches ollama.com
  • The prompt must not leave the machine

What it does

Glimmer Delegation is an agent skill from athola/claude-night-market. Delegates tasks to a locally served Muse Glimmer via ollama. Use when delegation-core selects glimmer or the prompt must not leave the machine.

Its SKILL.md is about 990 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering LLM inference and serving. It works with Ollama. The repository describes itself as: 23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context… The licence is MIT.

When your agent uses it

  • Delegation-core selects glimmer
  • The prompt must not leave the machine

Example prompts

  • “Use the glimmer-delegation skill to delegate tasks to a locally served Muse Glimmer via ollama”
  • “/glimmer-delegation”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 9f3eb00. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • ollama
    • curl
    • sh
    • uv
    • make

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • ollama.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Glimmer Delegation loads about 988 tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 440 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~988

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePipes a well-known installer script into a shellSKILL.md:55
    curl -fsSL https://ollama.com/install.sh | sh

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from athola/claude-night-market at commit 9f3eb00, republished under its MIT licence (© athola). 440 words, ~988 tokens.

Download SKILL.mdSave it as .claude/skills/glimmer-delegation/SKILL.md (or your agent's skills folder).
name
glimmer-delegation
description
Delegates tasks to a locally served Muse Glimmer via ollama. Use when delegation-core selects glimmer or the prompt must not leave the machine.
alwaysApply
false
category
delegation-implementation
tags
glimmer, ollama, local, delegation
dependencies
delegation-core
tools
ollama, delegation_executor.py
usage_patterns
local-model-delegation, offline-fallback
complexity
intermediate
model_hint
standard
estimated_tokens
550
references
delegation-core/shared-shell-execution.md

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
bash
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
bash
uv run python scripts/delegation_executor.py glimmer "Summarize" \
  --files src/
Through the Makefile
bash
make -C plugins/conjure delegate-glimmer PROMPT='Summarize' FILES='src/'
Direct CLI usage
bash
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.

Show full SKILL.md (206 more words)Show less

Glimmer-Specific Details

PropertyValue
Binaryollama
Headless formollama run muse-glimmer:30b
Prompt deliverystdin
File contextinlined into the prompt
Version probeollama --version
Auth probenone
Output format flag--format
Model flagnone

Read off ollama run --help at 0.13.1: the usage line is ollama run MODEL [PROMPT] [flags], so the model is positional and is carried by the subcommand. The flag list has no --model, which is why this service declares model_flag=None; passing one exits 1 on an unknown flag. --format string is documented there and is the reason output_format_flag is --format rather than the registry default --output-format, which the same CLI rejects.

No temperature flag is declared. ollama run --help documents none, and inventing one is the error class install_hint and login_hint already guard against.

Exit Criteria

  • ollama resolves on PATH and answers ollama --version
  • ollama list includes muse-glimmer:30b before a task is delegated; an absent model stops execution with the pull command rather than failing inside the delegation
  • The built command is ollama run muse-glimmer:30b with the prompt on stdin and no prompt flag
  • No --model flag appears in the built command
  • Output saved to delegations/glimmer/YYYYMMDD_HHMMSS.md
  • This skill ran because delegation-core selected glimmer, or because the prompt was required to stay local

© athola, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/conjure/skills/glimmer-delegation of athola/claude-night-market.

Open the folder on GitHubat commit 9f3eb00

Compare with similar skills

Glimmer Delegation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Glimmer Delegation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Glimmer Delegation this skillathola/claude-night-market341—~988Automated safety check: NotesMIT
Pudu Task Telemetrydavila7/claude-code-templates33k—~1.3kAutomated safety check: PassMIT
Agent Frameworkjihadkhawaja/Egroo178—~1.9kAutomated safety check: PassApache-2.0
QuorumDetrol/quorum-cli119—~807Automated safety check: NotesCustom licence
Ollama MCP Tool for NanoClawnanocoai/nanoclaw31k—~3kAutomated safety check: NotesMIT
Open Weightsericrisco/rsc-harness180—~4.1kAutomated safety check: PassMIT

Similar skills

  • Pudu Task Telemetry

    davila7/claude-code-templates

    Measure local AI task latency, token usage, errors and verified outcomes using Pudu AI hardware evidence and installed Ollama models.

    33k GitHub stars~1.3k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Agent Framework

    jihadkhawaja/Egroo

    Build, extend, and debug AI agents in Egroo using the Microsoft Agent Framework (C .NET).

    178 GitHub stars~1.9k tokensUpdated 6 mo ago
    AI & LLM EngineeringAuto-check passed
  • Quorum

    Detrol/quorum-cli

    Run a structured debate between agent CLIs (claude, codex, agy, grok) and the user's configured API or local models (OpenAI, Anthropic, Google, xAI, OpenRouter, Ollama and more) through the Quorum…

    119 GitHub stars~807 tokensUpdated 14 days ago
    AI & LLM EngineeringAuto-check: notes
  • Adds an MCP server so the NanoClaw container agent can send prompts to local Ollama models, with optional tools to manage the model library.

    31k GitHub stars~3k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check: notes
  • Open Weights

    ericrisco/rsc-harness

    A skill your agent uses when choosing an open-weight LLM and clearing it for use — which family and size fit the task, the hardware and the budget, and above all whether the license permits shipping.

    180 GitHub stars~4.1k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Mirofish Offline Simulation

    LeoYeAI/openclaw-master-skills

    Fully local multi-agent swarm intelligence simulation engine using Neo4j + Ollama for public opinion, market sentiment, and social dynamics prediction.

    2.2k GitHub stars~4.1k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check: notes

More from athola/claude-night-market

All 152 skills in this repo
  • Night Market Diagnostics Toolkit

    athola/claude-night-market

    Run and interpret repo diagnostic scripts (ratchets, validators, token stats).

    341 GitHub stars~3.4k tokensUpdated yesterday
    Auto-check passed
  • Skills Eval

    athola/claude-night-market

    Evaluate Claude skill quality through auditing. An agent skill from athola/claude-night-market.

    341 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • Agent Teams

    athola/claude-night-market

    Coordinates Claude agent teams via filesystem protocol. An agent skill from athola/claude-night-market.

    341 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed
  • Delegation Core

    athola/claude-night-market

    Delegates execution to eight CLIs (Gemini, Qwen, MiniMax, GLM, Muse, Codex, OpenCode, Glimmer).

    341 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed
  • Elegant Code

    athola/claude-night-market

    Guide minimal code via a decision ladder with full safety, edge, and negative-case coverage.

    341 GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed
  • Skill Library Mission

    athola/claude-night-market

    Build a project skill library in .claude/skills/ via discovery, parallel authoring, and review.

    341 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Glimmer Delegation

What does Glimmer Delegation do?

Delegates tasks to a locally served Muse Glimmer via ollama. Glimmer Delegation is an agent skill from athola/claude-night-market. Delegates tasks to a locally served Muse Glimmer via ollama.

When should I use Glimmer Delegation?

Glimmer Delegation fits situations like: delegation-core selects glimmer; the prompt must not leave the machine.

How do I install Glimmer Delegation in Claude Code?

Run `npx skills add athola/claude-night-market --skill glimmer-delegation -a claude-code`. Or copy the skill folder (plugins/conjure/skills/glimmer-delegation in athola/claude-night-market) into .claude/skills/glimmer-delegation in your project. Claude Code loads it when a task matches its description.

How do I install Glimmer Delegation in Codex?

Run `npx skills add athola/claude-night-market --skill glimmer-delegation -a codex`. Or copy the skill folder (plugins/conjure/skills/glimmer-delegation in athola/claude-night-market) into .agents/skills/glimmer-delegation in your project. Codex loads it when a task matches its description.

Can I use Glimmer Delegation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add athola/claude-night-market --skill glimmer-delegation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/glimmer-delegation, .gemini/skills/glimmer-delegation, .github/skills/glimmer-delegation and .opencode/skills/glimmer-delegation in your project.

What does Glimmer Delegation need to run?

Going by SKILL.md and its folder, Glimmer Delegation needs the command-line tools its instructions call (ollama, curl, sh, uv and make). Our summary lists: Python 3.

Does Glimmer Delegation access the network?

SKILL.md names 1 domain. In commands or code: ollama.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Glimmer Delegation safe to install?

Our automated static check of SKILL.md found notes only (pipes a well-known installer script into a shell), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Glimmer Delegation use?

Glimmer Delegation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Glimmer Delegation use?

About 988 tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Glimmer Delegation?

Skills that share tags, products or a category with Glimmer Delegation: Pudu Task Telemetry (davila7/claude-code-templates, 33k stars), Agent Framework (jihadkhawaja/Egroo, 178 stars), Quorum (Detrol/quorum-cli, 119 stars) and Ollama MCP Tool for NanoClaw (nanocoai/nanoclaw, 31k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Glimmer Delegation?

athola (a GitHub user) maintains it in athola/claude-night-market, which has 341 GitHub stars. The repository holds 152 skills in this directory. The repository was last updated on October 9, 2026.

Source: athola/claude-night-market on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.