Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add aiguicai/MCP-Gateway --skill task-planninggit clone --depth 1 https://github.com/aiguicai/MCP-GatewayWrote 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.
[](https://agentmods.dev/skills/aiguicai/mcp-gateway/task-planning)<a href="https://agentmods.dev/skills/aiguicai/mcp-gateway/task-planning"><img src="https://agentmods.dev/badge/skills/aiguicai/mcp-gateway/task-planning/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.
<a href="https://agentmods.dev/skills/aiguicai/mcp-gateway/task-planning"><img src="https://agentmods.dev/badge/skills/aiguicai/mcp-gateway/task-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.00979 |
| Opus 5 | $0.00016 | $0.00490 |
| Sonnet 5 | $0.00006 | $0.00196 |
| Haiku 4.5 | $0.00003 | $0.00098 |
Grade A, and why
task-planning scanned grade A with 0 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
- First read this complete SKILL.md and use the returned
skillToken. - Before a real bundled tool call, call
task-planningwithaction: "update"and the current todo list. - Use the returned
planningIdon the next real bundled tool call. - Reuse the same
planningIdacross multiple tool calls while working through the plan. It does not expire after successful tool calls. - Do not update the plan after every tool call just because a tool ran. A single plan step may require many tool calls.
- The gateway may include a single
planningReminderfield on successful bundled tool results. It only refers to the currentin_progressitem and may include a conciseset_statuscall to mark that item completed. - If the same
planningIdusesshell_commandthree or more times in a row without a plan update or another successful bundled tool, the gateway may includeshellCommandReminder. Use it as a nudge to combine related shell commands, read multiple files in one pass when useful, or prefer efficient search commands such asrgandrg --files. A shell command that starts withrgresets this counter. - If
multi_edit_filefails three or more times in a row for the sameplanningId, the gateway may includeeditFailureReminder. 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. - If the approach or step list changes, call
action: "update"with the new plan and use the returned newplanningId. Stop using the oldplanningId; clear it if needed. - Use
action: "set_status"for simple state changes. Ifitemis omitted, it updates the currentin_progressitem. When that item is set tocompletedand pending items remain, the gateway automatically starts the next pending item asin_progressand returns it asnextItem. - When every plan item is updated to
completed, the gateway closes thatplanningIdand 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.
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.
- 9d ago First seen · 91 lines · 32 tokens per session scan A 10e7549ddd91
task-planning is a skill published in the GitHub repository aiguicai/MCP-Gateway (154 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 979 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…