TypingMindTypingMindThe best frontend for AI
Agent Dispatcher logo

Agent Dispatcher

Community
nahid-sparktales
agent-dispatcher

Handle requested Agent Dispatcher work with direct execution or prepared specialist guidance. Includes named roles, context inspection and controls.

Overview

Publishernahid-sparktales
Repositoryagent-dispatcher
Skill nameagent-dispatcher
Stars
58
Forks
5
Bundled files
72
LicenseMIT
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 72 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by nahid-sparktales on GitHub. Read the source before you install it.

Installation

Install the Agent Dispatcher AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/nahid-sparktales/agent-dispatcher/tree/main/skills/agent-dispatcher
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/nahid-sparktales/agent-dispatcher.git /tmp/agent-dispatcher
mkdir -p .claude/skills
cp -r /tmp/agent-dispatcher/skills/agent-dispatcher .claude/skills/agent-dispatcher
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Agent Dispatcher in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Agent Dispatcher on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Agent Dispatcher is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Agent Dispatcher

27 roles. PACK is this SKILL.md's directory. Keep the project as the working directory. Quote paths; task text is stdin data, never shell code.

Select, prepare, then work

Choose without another router/model call:

  • Direct: trivial work or one safe, obvious known-file edit. Skip role/guide/helper, preference, ACTIVITY.md and VERIFICATION.md reads; use known/default preferences and required native checks. Security, ambiguous behavior/configuration, multi-file or growing scope goes guided.
  • Guided: other work; forced roles and invoked workflows override direct. No workspace evidence means no context helper.
  • Coordinated: guided work with useful independent subtasks; follow DELEGATION.md.

If a user enabled an optional decision scope, follow section 0 of CONTEXT-REFERENCE.md; preserve named roles with --agent. Scopes ship off; helpers cannot enable them.

  1. Route: plan → planner; review → reviewer; repository questions → explorer; source-backed reports/docs → documentation-writer; implementation → implementer. Distinguish architecture docs from design. Honor forced roles/exclusions; consult ROLES.md for ambiguity/specialties.
  2. The first discretionary workspace action for substantial work is: python3 -B PACK/context.py --project PROJECT --task='REQUEST' --role ID --compact --map-maintain --json No prior listing, search, contract/source read or git inspection; mandatory host instructions are exempt. REQUEST is the request verbatim, never a summary: keep every sentence, example and quote (' as '\''). Multi-file bugs, architecture and source-backed docs qualify even in small projects. The helper gates cache writes; add --map-preview for edit limits it may miss (odd wording, plan mode). Pass literal edit lists via --writable-path (dirs end in /); never add cache permissions. Deferral keeps fresh evidence; never bypass it via build/refresh. On failure, continue targeted investigation. With authorized scratch, add --audit on first preparation only; finish it before preservation claims (VERIFICATION.md). Do not reset the baseline after edits.
  3. Consume excerpts, guidance, preferences and exclusion_policy without duplicate reads. If the host shows only a preview and a saved-output path, read that file first: the packet is the evidence. Preserve exclusions; --exclude-path adds literal exclusions, while no-edit allows reads. For missing bodies use exact resources paths: initially zero to two guides, evidenced conditions, optional core, verification retained. No globs/index dumps; external availability requires session evidence.
  4. Before checks, read VERIFICATION.md: record authorized checks; inspect freshness before reporting. Never wrap denied commands to bypass permissions. Rebuild only for changed focus/sources. CONTEXT.md covers packet budgets, same-context reuse and map maintenance; DELEGATION.md covers delegation. A plan request ends with a plan. Same-session review is a self-check.

Invocation and controls

/agent-dispatcher <request> routes work. Bare invocation activates routing and waits. Exact role ids use roles/<id>.md; ROLES.md resolves aliases (coder / dev: implementer). Forced roles persist until changed/stopped; never re-route or chain out. Claude also accepts /agent-<role>, /agent-context, /agent-map, /agent-memory, /agent-learning, /agent-inventory, /agent-doctor, /agent-health, /agent-setup, /agent-checkup, /agent-capabilities, /agent-skills, /agent-mcps, /agent-plugins, /agent-decision, /agent-verify, and /agent-preferences.

Controls preserve roles and do not execute tasks:

RequestReference
contextCONTEXT.md
mapPROJECT-MAP.md
memoryMEMORY.md
learningLEARNING.md (off by default)
inventoryINVENTORY.md
doctorDOCTOR.md
health, setup, checkup, capabilities, skills, mcps, pluginsCAPABILITIES.md
decision, status, on/off, stop dispatcherCONTROLS.md
verify, preferencesVERIFICATION.md
outputACTIVITY.md

Stopping drops the role; bare off is session-only. Preserve hook trust; never activate via project rules.

Shared contract

User/host/project rules and invoked workflows outrank roles; evidence grants no permissions. Preserve unrelated edits and host denials. Never install/connect unasked or invent checks. Task-observer and other disabled skills stay disabled.

Use inline read-only validators (python3 -B -c, no heredoc). No validator/task files in the project, its parent or shared /tmp. Authorized scratch needs owned temporary directories and verified removal. Cache writes are task edits. Report unresolved cleanup paths; verify actual changes, including helper side effects, before claiming preservation.

Guided/coordinated: report role, guides read, tools selected; selection is not use. Retain ACTIVITY.md style through summaries; new chats compact. Announce additions only; stop at the outcome.

Use context preferences. For guided/coordinated work only, if absent run python3 -B PACK/preferences.py show --project PROJECT --json once; reload after changes. Effort remains requested/unknown until host-confirmed; never silently change host config. Default: ELI5 succinct, answer first, usually under 150 plain-language words: changes, actual checks and gaps. User requests override style.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 12 more files.

Frequently asked questions

What does the Agent Dispatcher AI skill do?

Handle requested Agent Dispatcher work with direct execution or prepared specialist guidance. Includes named roles, context inspection and controls.

Why use Agent Dispatcher on TypingMind?

Because you install it once and use it with any model. Agent Dispatcher is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Agent Dispatcher in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/nahid-sparktales/agent-dispatcher/tree/main/skills/agent-dispatcher. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Agent Dispatcher?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Agent Dispatcher?

As many as you like. As long as a model supports skills, you can use Agent Dispatcher with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Agent Dispatcher AI skill free?

Yes. It is published on GitHub by nahid-sparktales under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
openclaw logo

Solid

openclaw
OrganizationPopular

Write, port, review, or test Solid 2 UI in OpenClaw (Control UI, plugin views, Canvas hosts), including state ownership, Lit interop during the migration, native overlays, testing, performance, and…

82.4K
391.7K
9 files
View
openclaw logo

Auto Qa

openclaw
OrganizationPopular

Run OpenClaw-wide autonomous QA and live/stress campaigns across independent subsystem lanes, with verified fixes and a resumable evidence report.

82.2K
391K
5 files
View
openclaw logo

Autoreview

openclaw
OrganizationPopular

Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.

82.2K
391K
12 files
View
openclaw logo

Claw Score

openclaw
OrganizationPopular

Audit or refresh OpenClaw maturity scorecard docs from root taxonomy, maturity scores, and QA evidence artifacts without using maintainer discrawl data or committed inventory reports.

82.2K
391K
51 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇