Agent skill

Task Planning

by aiguicai in aiguicai/MCP-Gateway

Use this bundled skill to create, update, and clear the in-memory todo state required before real bundled tool calls when task planning is enabled.

MITAuto-check passedAgent Workflows

Install Task Planning

skills CLI
$ npx skills add aiguicai/MCP-Gateway --skill task-planning -a claude-code

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

GitHub CLI
$ gh skill install aiguicai/MCP-Gateway task-planning --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/aiguicai/MCP-Gateway.git skills-src && mkdir -p .claude/skills && cp -r skills-src/mcp-gateway/crates/gateway-http/builtin-skills/task-planning .claude/skills/task-planning && 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
task-planning
GitHub stars
158
Token cost
~1.1k tokens
SKILL.md length
508 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Use this bundled skill to create, update, and clear the in-memory todo state required before real bundled tool calls when task planning is enabled.

  • Works in 11 steps: First read this complete SKILL.md and… → Before a real bundled tool call, call… → Use the returned planningId on the next… → …
  • Tasks that involve Planning
  • SKILL.md covers Workflow, Status Values and Suggested Format
  • Calls rg

What it does

Task Planning is an agent skill from aiguicai/MCP-Gateway. Use this bundled skill to create, update, and clear the in-memory todo state required before real bundled tool calls when task planning is enabled.

Its SKILL.md is about 1.1k 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 Agent Workflows, covering Planning. The repository describes itself as: Unify multiple MCP Servers & Skills into a single gateway — with proxy forwarding, authentication, and a management API. Typical use: expose local stdio servers as remote MCP… The licence is MIT.

When your agent uses it

  • Tasks that involve Planning

Example prompts

  • “/task-planning”

Workflow steps

11 steps, taken from the first numbered list in SKILL.md.

  1. First read this complete SKILL.md and use the returned skillToken.
  2. Before a real bundled tool call, call task-planning with action: "update" and the current todo list.
  3. Use the returned planningId on the next real bundled tool call.
  4. Reuse the same planningId across multiple tool calls while working through the plan. It does not expire after successful tool calls.
  5. Do not update the plan after every tool call just because a tool ran. A single plan step may require many tool calls.
  6. The gateway may include a single planningReminder field on successful bundled tool results. It only refers to the current in_progress item…
  7. If the same planningId uses shell_command three or more times in a row without a plan update or another successful bundled tool, the…
  8. If multi_edit_file fails three or more times in a row for the same planningId, the gateway may include editFailureReminder. Use it as a…
  9. If the approach or step list changes, call action: "update" with the new plan and use the returned new planningId. Stop using the old…
  10. Use action: "set_status" for simple state changes. If item is omitted, it updates the current in_progress item. When that item is set to…
  11. When every plan item is updated to completed, the gateway closes that planningId and it can no longer be used for real bundled tool calls…

What it can do on your machine

Read from SKILL.md and the folder at commit 9cfc330. 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:

    • rg

    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

Task Planning loads about 1.1k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 508 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
~1.1k

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 aiguicai/MCP-Gateway at commit 9cfc330, republished under its MIT licence (© aiguicai). 508 words, ~1,051 tokens.

Download SKILL.mdSave it as .claude/skills/task-planning/SKILL.md (or your agent's skills folder).
name
task-planning
description
Use this bundled skill to create, update, and clear the in-memory todo state required before real bundled tool calls when task planning is enabled.
metadata.short-description
Lightweight todo planning workflow

Task Planning

Use this skill when bundled tool calls require a plan. The gateway stores a lightweight in-memory plan state per client/session and per content-derived planningId. It does not persist plans across gateway restarts and it does not render UI.

Workflow

  1. First read this complete SKILL.md and use the returned skillToken.
  2. Before a real bundled tool call, call task-planning with action: "update" and the current todo list.
  3. Use the returned planningId on the next real bundled tool call.
  4. Reuse the same planningId across multiple tool calls while working through the plan. It does not expire after successful tool calls.
  5. Do not update the plan after every tool call just because a tool ran. A single plan step may require many tool calls.
  6. The gateway may include a single planningReminder field on successful bundled tool results. It only refers to the current in_progress item and may include a concise set_status call to mark that item completed.
  7. If the same planningId uses shell_command three or more times in a row without a plan update or another successful bundled tool, the gateway may include shellCommandReminder. Use it as a nudge to combine related shell commands, read multiple files in one pass when useful, or prefer efficient search commands such as rg and rg --files. A shell command that starts with rg resets this counter.
  8. If multi_edit_file fails three or more times in a row for the same planningId, the gateway may include editFailureReminder. Use it as a nudge to inspect exact file content, simplify the operation, split unrelated changes, or fall back to a focused shell script when structured edits keep failing.
  9. If the approach or step list changes, call action: "update" with the new plan and use the returned new planningId. Stop using the old planningId; clear it if needed.
  10. Use action: "set_status" for simple state changes. If item is omitted, it updates the current in_progress item. When that item is set to completed and pending items remain, the gateway automatically starts the next pending item as in_progress and returns it as nextItem.
  11. When every plan item is updated to completed, the gateway closes that planningId and it can no longer be used for real bundled tool calls. Then omit the temporary todo list from the final response unless the user asks for it.
Show full SKILL.md (115 more words)Show less

Status Values

Use these status labels when showing a checklist:

  • pending - not started yet
  • in_progress - currently being worked on
  • completed - finished and no longer active

Suggested Format

json
{
  "action": "update",
  "explanation": "Starting the implementation",
  "plan": [
    { "step": "Inspect existing skill registration", "status": "completed" },
    { "step": "Add the planning gate", "status": "in_progress" },
    { "step": "Run focused tests", "status": "pending" }
  ],
  "skillToken": "<token from this SKILL.md>"
}

The response includes:

json
{
  "planning": {
    "planningId": "plan-..."
  }
}

Pass those fields to the next real bundled tool call:

json
{
  "planningId": "plan-..."
}

For concise status updates, prefer set_status instead of sending the full plan again:

json
{
  "action": "set_status",
  "planningId": "plan-...",
  "status": "completed",
  "skillToken": "<token from this SKILL.md>"
}

That marks the current in_progress item as completed. If more work remains, the response includes nextItem; continue with that item using the same planningId. To update a specific array item, use a 1-based item number:

json
{
  "action": "set_status",
  "planningId": "plan-...",
  "item": 2,
  "status": "in_progress",
  "skillToken": "<token from this SKILL.md>"
}

For final responses, summarize what changed and any verification performed. Do not keep the planning checklist in the final answer unless the user explicitly asks for it.

© aiguicai, 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 mcp-gateway/crates/gateway-http/builtin-skills/task-planning of aiguicai/MCP-Gateway.

Open the folder on GitHubat commit 9cfc330

Compare with similar skills

Task Planning 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.

Task Planning compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Task Planning this skillaiguicai/MCP-Gateway158—~1.1kAutomated safety check: PassMIT
Executing Plans Inlineobra/superpowers296k2 repos~5.1kAutomated safety check: PassMIT
Interview Meaddyosmani/agent-skills103k6 repos~3.8kAutomated safety check: PassMIT
OpenSpec Guided OnboardingFission-AI/OpenSpec71k1 repos~4.5kAutomated safety check: PassMIT
Writing Plansgeeksblabla/stateofdev.ma16357 repos~661Automated safety check: PassNone
Subagent Driven DevelopmentAsvarox/allkaraoke26138 repos~1.2kAutomated safety check: PassNone

Similar skills

  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    296k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed
  • Interview Me

    addyosmani/agent-skills

    Asks one question at a time, each with a best guess attached, until the agent is about 95 percent sure what you really want, before any plan, spec or code.

    103k GitHub starsUsed in 6 repos~3.8k tokens
    Agent WorkflowsAuto-check passed
  • OpenSpec Guided Onboarding

    Fission-AI/OpenSpec

    Walks you through a complete OpenSpec workflow cycle with narration while doing real work in your codebase.

    71k GitHub starsUsed in 1 repo~4.5k tokens
    Agent WorkflowsAuto-check passed
  • Writing Plans

    geeksblabla/stateofdev.ma

    A skill your agent uses when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file…

    163 GitHub starsUsed in 57 repos~661 tokens
    Agent WorkflowsAuto-check passed
  • Subagent Driven Development

    Asvarox/allkaraoke

    A skill your agent uses when executing implementation plans with independent tasks in the current session

    261 GitHub starsUsed in 38 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Planning With Files

    jd-opensource/JoySafeter

    Implements Manus-style file-based planning for complex tasks.

    313 GitHub starsUsed in 19 repos~1.8k tokens
    Agent WorkflowsAuto-check: notes

More from aiguicai/MCP-Gateway

  • Chrome Cdp

    aiguicai/MCP-Gateway

    Browser automation and debugging through bundled Chrome DevTools Protocol.

    158 GitHub stars~2.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Chat Plus Adapter Debugger

    aiguicai/MCP-Gateway

    为 Chat Plus 新框架编写、修复、审查站点适配脚本。先读取完整 builtin://chat-plus-adapter-debugger/SKILL.md 获取 skillToken;这次读取 SKILL.md 不需要 skillToken。不要用正则或局部读取只抓 token。后续调用不带或带错 skillToken 会报错并必须重试,所以正式调试前先拿到正确 token。

    158 GitHub stars~3.8k tokensUpdated 4 mo ago
    Auto-check passed
  • Codegraph

    aiguicai/MCP-Gateway

    Run CodeGraph CLI commands through npx for local codebase indexing, semantic search, context building, and impact analysis.

    158 GitHub stars~1.3k tokensUpdated 4 mo ago
    Auto-check passed
  • Officecli

    aiguicai/MCP-Gateway

    Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool.

    158 GitHub stars~7.1k tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Task Planning

What does Task Planning do?

Use this bundled skill to create, update, and clear the in-memory todo state required before real bundled tool calls when task planning is enabled. Task Planning is an agent skill from aiguicai/MCP-Gateway. Use this bundled skill to create, update, and clear the in-memory todo state required before real bundled tool calls when task planning is enabled.

When should I use Task Planning?

Task Planning fits situations like: tasks that involve Planning.

How do I install Task Planning in Claude Code?

Run `npx skills add aiguicai/MCP-Gateway --skill task-planning -a claude-code`. Or copy the skill folder (mcp-gateway/crates/gateway-http/builtin-skills/task-planning in aiguicai/MCP-Gateway) into .claude/skills/task-planning in your project. Claude Code loads it when a task matches its description.

How do I install Task Planning in Codex?

Run `npx skills add aiguicai/MCP-Gateway --skill task-planning -a codex`. Or copy the skill folder (mcp-gateway/crates/gateway-http/builtin-skills/task-planning in aiguicai/MCP-Gateway) into .agents/skills/task-planning in your project. Codex loads it when a task matches its description.

Can I use Task Planning 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 aiguicai/MCP-Gateway --skill task-planning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/task-planning, .gemini/skills/task-planning, .github/skills/task-planning and .opencode/skills/task-planning in your project.

What does Task Planning need to run?

Going by SKILL.md and its folder, Task Planning needs the command-line tools its instructions call (rg).

Does Task Planning 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 Task Planning 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 Task Planning use?

Task Planning 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 Task Planning use?

About 1.1k tokens (SKILL.md is roughly 4.2k 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 Task Planning?

Skills that share tags, products or a category with Task Planning: Executing Plans Inline (obra/superpowers, 296k stars), Interview Me (addyosmani/agent-skills, 103k stars), OpenSpec Guided Onboarding (Fission-AI/OpenSpec, 71k stars) and Writing Plans (geeksblabla/stateofdev.ma, 163 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Task Planning?

aiguicai (a GitHub organization) maintains it in aiguicai/MCP-Gateway, which has 158 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on May 27, 2026.

Source: aiguicai/MCP-Gateway on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.