A planning step that turns an approved feature description into a technical design and a staged implementation roadmap. It also records research and defines the checks each stage must pass.

Use it to research a feature, create PLAN.md and TECH.md files, and prepare a phased workflow for later coding.

It gives a coding task a reviewed design and sequence before implementation begins, reducing uncertainty about what to build.

How PurdueRCAC/globus-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to PurdueRCAC/globus-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/PurdueRCAC/globus-mcp/main/.agents/skills/globus-plan/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/PurdueRCAC/globus-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/purduercac/globus-mcp/globus-plan/github.svg)](https://agentmods.dev/skills/purduercac/globus-mcp/globus-plan)

Your own site

<a href="https://agentmods.dev/skills/purduercac/globus-mcp/globus-plan"><img src="https://agentmods.dev/badge/skills/purduercac/globus-mcp/globus-plan/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/purduercac/globus-mcp/globus-plan"><img src="https://agentmods.dev/badge/skills/purduercac/globus-mcp/globus-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,248 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00102	$0.03248
Opus 5	$0.00051	$0.01624
Sonnet 5	$0.00020	$0.00650
Haiku 4.5	$0.00010	$0.00325

Measured 9d ago against content hash 1c5b0d8349de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

globus-plan 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.

.agents/skills/globus-plan/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

globus-plan — research → PLAN → TECH

When to Use

Invoke /globus-plan after /globus-feature has landed a quality GOAL.md on a feature/fix branch. It produces the design (PLAN.md), optional backing research/, and the phased FSM (TECH.md), then stops for your sign-off before /globus-build touches code. Depth scales to the GOAL's appetite.

Reference: .agents/factory/methodology.md, .agents/factory/invariants.md (the gate), templates PLAN.md / TECH.md.

Harness portability. Runs on any harness — see factory/portability.md. Fallbacks: if the Current state block isn't auto-injected, run those commands yourself in Step 1; ask in plain text and STOP if AskUserQuestion is unavailable; and if subagents are unavailable, do the research fan-out sequentially yourself (Step 3 gives the fallback). Everything else is portable shell.

User Instructions

Additional instructions provided with the invocation: $ARGUMENTS

Current state (injected at load)

Branch: !git branch --show-current
Tree: !git status --porcelain | head -n 20
Spec artifacts: !ls -1 spec/*/ 2>/dev/null | head -n 40

Argument Parsing

skip research / no research → collapse to a lean plan (no fan-out) regardless of appetite.
appetite small|big → override the GOAL's appetite for this planning run.
status / report → summarize what artifacts already exist for this slug and what's missing; no work.

Safety Principles

On a feature/fix branch, never main. Derive {slug} = branch minus its feature/|fix/ prefix. STOP if on the base branch or the tree is dirty.
GOAL.md must exist, be committed, and carry no unresolved [NEEDS CLARIFICATION] markers. If markers remain, STOP and send the human back to /globus-feature.
Research is strictly read-only and biased to the codebase (this is a small, self-contained package). Reach for the web when the unknown genuinely is external — Globus CLI flag semantics, Globus Transfer/Compute API behavior, FastMCP schema generation — since those are upstream contracts this repo only wraps. Keep briefs minimal.
Research never touches production. A read-only researcher may not run globus against a live service, may not instantiate globus_compute_sdk.Client(), and may not call a tool through the server with real credentials. Read the code and the upstream docs; if a question can only be answered by a live call, record it in PLAN § Risks & open questions for the human.
Never build. No source edits, no implementation. That's /globus-build.
The invariant gate is mandatory (both checkpoints). Any bend gets recorded in PLAN's deviation table, never applied silently.

Read the full file on GitHub · 199 lines

Changes

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 · 199 lines · 102 tokens per session scan A 1c5b0d8349de

Subscribe to this mod's changes

globus-plan is a skill published in the GitHub repository PurdueRCAC/globus-mcp (1 stars, last pushed 13d ago), licensed MIT. It adds 102 tokens to every session and 3,248 once invoked, about $0.0005 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 2026-08-31.

Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

globus-mcp: Skill for Claude Code