Agent skill

Delegation Core

by athola in athola/claude-night-market

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

MITAuto-check passedAgent Workflows

Install Delegation Core

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

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

GitHub CLI
$ gh skill install athola/claude-night-market delegation-core --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/delegation-core .claude/skills/delegation-core && 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
delegation-core
GitHub stars
341
Token cost
~2.5k tokens
SKILL.md length
1,037 words
Files
8 (incl. references)
Skills in repo
154
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 4 steps: Task Assessment… → Suitability Evaluation… → Handoff Planning… → …
  • Execution tasks
  • SKILL.md covers Overview, Default Posture, Keep Local and Declining Delegation, plus 12 more sections
  • Calls claude and make

What it does

Delegation Core is an agent skill from athola/claude-night-market. Delegates execution to eight CLIs (Gemini, Qwen, MiniMax, GLM, Muse, Codex, OpenCode, Glimmer). Use for execution tasks. Do not use for secrets.

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including reference files (for example `modules/cost-estimation.md`, `modules/handoff-patterns.md` and `modules/provider-onboarding.md`).

It sits in Agent Workflows. It works with MiniMax and Qwen. 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

  • Execution tasks

Example prompts

  • “Use the delegation-core skill to delegate execution to eight CLIs (Gemini, Qwen, MiniMax, GLM, Muse, Codex, OpenCode, Glimmer)”
  • “/delegation-core”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Task Assessment (delegation-core:task-assessed)
  2. Suitability Evaluation (delegation-core:delegation-suitability)
  3. Handoff Planning (delegation-core:handoff-planned)
  4. Execution & Integration (delegation-core:results-integrated)

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:

    • claude
    • make

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

  • Network

    No URLs in SKILL.md.

    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

Delegation Core loads about 2.5k tokens when it runs, and up to ~4.8k if it reads all its reference files. Until then it costs about 40 tokens; SKILL.md has 1,037 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~40
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.8k

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 passed

The automated check found no risky patterns in SKILL.md.

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). 1,037 words, ~2,474 tokens.

Download SKILL.mdSave it as .claude/skills/delegation-core/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
delegation-core
description
Delegates execution to eight CLIs (Gemini, Qwen, MiniMax, GLM, Muse, Codex, OpenCode, Glimmer). Use for execution tasks. Do not use for secrets.
alwaysApply
false
category
delegation-framework
tags
delegation, external-llm, gemini, qwen, minimax, glm, muse, codex, opencode, task-management, quality-control
dependencies
leyline:quota-management, leyline:usage-logging, leyline:service-registry, leyline:error-patterns, leyline:authentication-patterns
usage_patterns
task-assessment, delegation-planning, quality-validation, integration-workflows
complexity
intermediate
model_hint
standard
estimated_tokens
600
progressive_loading
true
modules
modules/provider-onboarding.md, modules/task-assessment.md, modules/cost-estimation.md, modules/handoff-patterns.md, modules/troubleshooting.md

Delegation Core Framework

Overview

A method for deciding when and how to delegate tasks to external LLM services. Core principle: delegate execution, retain high-level reasoning.

Default Posture

Delegation is on. Declining it is the step that takes a decision.

Any conjure operation, mission phase, or workflow that reaches eligible work delegates it without being asked. Eligible means the work is execution rather than reasoning, which the philosophy below defines and modules/task-assessment.md classifies. An operator who wants delegation off says so once, in one of the two places under Declining Delegation.

This inverts the earlier framing, which listed the occasions on which to delegate and so made delegation something a caller had to remember. The occasions were correct and are now the exception list instead.

Keep Local

Delegation stops at the boundary the philosophy draws. Keep the work local when any of these hold:

  • The task is reasoning: architecture, design, trade-offs, judgment.
  • The prompt or context carries a secret, a credential, or data that should not leave the machine.
  • The task needs iteration with the operator turn by turn.
  • Correctness cannot be validated after the fact.

The first is the standing exception and covers most of what Claude does. The rest are the red flags modules/task-assessment.md already lists.

Declining Delegation

Two switches, environment over file.

ScopeHowEffect
One runCONJURE_DELEGATION=offNo provider is probed or spawned
One machine"enabled": false in ~/.claude/hooks/delegation/config.jsonSame, until the key changes

CONJURE_DELEGATION accepts off, 0, false, no and their opposites, in any case. Setting it to an on spelling re-enables delegation that the config file turned off, so the narrower scope wins. A disabled delegator returns a result whose fallback_reason is delegation_disabled and spawns nothing, so opting out costs nothing.

When No Provider Answers

smart_delegate works down the registry order and returns the first real answer. A provider that is missing, unauthenticated, failing, or answering with an empty stdout is recorded and the chain moves on.

When it reaches the end, it returns a result with fallback_reason set to providers_exhausted and an attempts trail naming what each provider did. That result is the instruction to do the work locally. Read it, say which providers were tried and why none answered, and then do the task yourself. Do not treat it as an error to report and stop on: a machine with no CLI installed is the ordinary case for this default, not a fault.

When the operator wants providers answering rather than falling back, modules/provider-onboarding.md carries the per-provider steps and the failure shapes that do not look like authentication problems. Start with make -C plugins/conjure delegate-doctor.

Philosophy

Delegate execution, retain reasoning. Claude handles architecture, strategy, design, and review. External LLMs perform data processing, pattern extraction, bulk operations, and summarization.

Delegation Flow

  1. Task Assessment: Classify task by complexity and context size.
  2. Suitability Evaluation: Check prerequisites and service fit.
  3. Handoff Planning: Formulate request and document plan.
  4. Execution & Integration: Run delegation, validate, and integrate results.

Quick Decision Matrix

ComplexityContextRecommendation
HighAnyKeep local
LowLargeDelegate
LowSmallEither

High Complexity: Architecture, design decisions, trade-offs, creative problem solving.

Low Complexity: Pattern counting, bulk extraction, boilerplate generation, summarization.

Detailed Workflow Steps

1. Task Assessment (delegation-core:task-assessed)

Classify the task:

  • See modules/task-assessment.md for classification criteria.
  • Use token estimates to determine thresholds.
  • Apply the decision matrix.

Exit Criteria: Task classified with complexity level, context size, and delegation recommendation.

2. Suitability Evaluation (delegation-core:delegation-suitability)

Verify prerequisites:

  • See modules/handoff-patterns.md for checklist.
  • Evaluate cost-benefit ratio using modules/cost-estimation.md.
  • Check for red flags (security, real-time iteration).

Exit Criteria: Service authenticated, quotas verified, cost justified.

3. Handoff Planning (delegation-core:handoff-planned)

Create a delegation plan:

  • See modules/handoff-patterns.md for request template.
  • Document service, command, input context, expected output.
  • Define validation method.

Exit Criteria: Delegation plan documented.

Show full SKILL.md (416 more words)Show less
4. Execution & Integration (delegation-core:results-integrated)

Execute and validate results:

  • Run delegation and capture output.
  • Validate format and correctness.
  • Integrate only after validation passes.
  • Log usage.

Exit Criteria: Results validated and integrated, usage logged.

MCP Authentication

OAuth Client Credentials (Claude Code 2.1.30+)

For MCP servers that don't support Dynamic Client Registration (e.g., Slack), pre-configured OAuth client credentials can be provided:

bash
claude mcp add <server-name> --client-id <id> --client-secret <secret>

This enables delegation workflows through MCP servers that require pre-configured OAuth, expanding the range of external services available for task delegation.

Claude.ai MCP Connectors (Claude Code 2.1.46+)

As an alternative to manual OAuth setup, users can configure MCP servers directly in claude.ai at claude.ai/settings/connectors. These connectors are automatically available in Claude Code when logged in with a claude.ai account: no claude mcp add or credential management required. This provides a browser-based auth flow that may be simpler for services with complex OAuth requirements.

Worktree Isolation for File-Modifying Delegations (Claude Code 2.1.49+)

When delegating tasks that modify files to subagents, use isolation: worktree in the agent frontmatter to run each agent in a temporary git worktree. This prevents file conflicts when multiple delegated agents operate in parallel on overlapping paths. The worktree is auto-cleaned if no changes are made; preserved with commits if the agent produces changes.

yaml
# Agent frontmatter for isolated delegation
isolation: worktree

Leyline Infrastructure

Conjure uses leyline infrastructure:

Leyline SkillUsed For
quota-managementTrack service quotas and thresholds.
usage-loggingSession-aware audit trails.
service-registryUnified service configuration.
error-patternsConsistent error handling.
authentication-patternsAuth verification.

See modules/cost-estimation.md for leyline integration examples.

Service-Specific Skills

For detailed service workflows:

  • Skill(conjure:gemini-delegation): Gemini CLI specifics.
  • Skill(conjure:qwen-delegation): Qwen MCP specifics.
  • Skill(conjure:minimax-delegation): MiniMax CLI specifics.
  • Skill(conjure:glm-delegation): GLM via the Z.ai endpoint swap.
  • Skill(conjure:muse-delegation): Meta Muse Code CLI specifics.
  • Skill(conjure:codex-delegation): OpenAI Codex CLI specifics.
  • Skill(conjure:opencode-delegation): OpenCode CLI specifics.

Execution Modes

When delegating to multiple agents, choose the appropriate execution mode:

ModeWhen to UseHow It Works
single-sessionSequential tasks, same-file editsClaude works through tasks in order
subagentsParallel independent tasksAgents work independently, report back
agent-teamParallel coordinated tasksAgents can communicate with each other

See references/execution-modes.md for the selection decision matrix, mode compatibility notes, and anti-patterns to avoid.

Module Reference

  • provider-onboarding.md: Install and auth per provider, and how to read a half-configured one.
  • task-assessment.md: Complexity classification, decision matrix.
  • cost-estimation.md: Pricing, budgets, cost tracking.
  • handoff-patterns.md: Request templates, workflows.
  • troubleshooting.md: Common problems, service failures.

Exit Criteria

  • Task assessed and classified.
  • Work that stayed local names which Keep Local clause held it.
  • A providers_exhausted result was reported with its attempts trail and then completed locally, not abandoned.
  • Results validated before integration.
  • Lessons captured.

© 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

SKILL.md and 7 other files (references) in plugins/conjure/skills/delegation-core of athola/claude-night-market.

  • SKILL.md
  • modules/cost-estimation.md
  • modules/handoff-patterns.md
  • modules/provider-onboarding.md
  • modules/task-assessment.md
  • modules/troubleshooting.md
  • references/execution-modes.md
  • shared-shell-execution.md

Open the folder on GitHubat commit 9f3eb00

Compare with similar skills

Delegation Core 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.

Delegation Core compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Delegation Core this skillathola/claude-night-market341—~2.5kAutomated safety check: PassMIT
Subagentethanhq/cc-fleet215—~4.9kAutomated safety check: PassApache-2.0
Subagentethanhq/cc-fleet215—~4.3kAutomated safety check: PassApache-2.0
Code Reviewtimwuhaotian/the-pair378—~250Automated safety check: PassMIT
Release Prepfinch-xu/cc-router272—~1.5kAutomated safety check: PassMIT
AI Search Hubminsight-ai-info/AI-Search-Hub1.3k—~1.3kAutomated safety check: PassNone

Similar skills

  • Subagent

    ethanhq/cc-fleet

    Fan out a one-shot or flat parallel batch of cc-fleet PROVIDER subagents (headless cc-fleet subagent) that return a result — DeepSeek / GLM / Kimi / Qwen / MiniMax, or a Codex/Claude subscription.

    215 GitHub stars~4.9k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed
  • Subagent

    ethanhq/cc-fleet

    Run a one-shot or flat parallel batch of provider LLM subagents (headless cc-fleet subagent) that return a result.

    215 GitHub stars~4.3k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed
  • Code Review

    timwuhaotian/the-pair

    Comprehensive code review with security and performance checks

    378 GitHub stars~250 tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • Release Prep

    finch-xu/cc-router

    cc-router 发版准备一条龙:升版本号 → 根据上一个 tag 以来的提交写 release-notes/<版本/ 的中英日三份更新内容 → 校验 → 给用户审 → 本地提交「Bump version to X.Y.Z」,停在打 tag 之前。当用户说「准备发版」「发个版」「发 6.1.0」「写发版说明 / 更新内容 / release notes」「bump 版本」时必须走本…

    272 GitHub stars~1.5k tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • AI Search Hub

    minsight-ai-info/AI-Search-Hub

    Run the AI Search Hub browser automation scripts for Yuanbao, LongCat, Doubao, Qwen, Gemini, Grok, and MiniMax.

    1.3k GitHub stars~1.3k tokensUpdated 5 mo ago
    Productivity & AutomationAuto-check passed
  • Agent Reproduce Align

    QwenLM/qwen-code

    Runs a reference agent (Codex or Claude Code) and Qwen Code on the same scenario, captures HTTP and terminal traces, and compares them until behavior matches.

    28k GitHub stars~1.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from athola/claude-night-market

All 154 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 3 days ago
    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 3 days ago
    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 3 days ago
    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 3 days ago
    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 3 days ago
    Auto-check passed
  • Mission Orchestrator

    athola/claude-night-market

    Orchestrates full project lifecycle by auto-detecting state and routing to the correct phase.

    341 GitHub stars~3.4k tokensUpdated 3 days ago
    Auto-check: warnings

Works with

Questions about Delegation Core

What does Delegation Core do?

Delegates execution to eight CLIs (Gemini, Qwen, MiniMax, GLM, Muse, Codex, OpenCode, Glimmer). Delegation Core is an agent skill from athola/claude-night-market. Delegates execution to eight CLIs (Gemini, Qwen, MiniMax, GLM, Muse, Codex, OpenCode, Glimmer).

When should I use Delegation Core?

Delegation Core fits situations like: execution tasks.

How do I install Delegation Core in Claude Code?

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

How do I install Delegation Core in Codex?

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

Can I use Delegation Core 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 delegation-core -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/delegation-core, .gemini/skills/delegation-core, .github/skills/delegation-core and .opencode/skills/delegation-core in your project.

What does Delegation Core need to run?

Going by SKILL.md and its folder, Delegation Core needs the command-line tools its instructions call (claude and make).

Does Delegation Core access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Delegation Core safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Delegation Core use?

Delegation Core 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 Delegation Core use?

About 2.5k tokens (SKILL.md is roughly 9.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.3k tokens, read only when the agent opens those files.

What are the alternatives to Delegation Core?

Skills that share tags, products or a category with Delegation Core: Subagent (ethanhq/cc-fleet, 215 stars), Subagent (ethanhq/cc-fleet, 215 stars), Code Review (timwuhaotian/the-pair, 378 stars) and Release Prep (finch-xu/cc-router, 272 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Delegation Core?

athola (a GitHub user) maintains it in athola/claude-night-market, which has 341 GitHub stars. The repository holds 154 skills in this directory. The repository was last updated on October 6, 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.