globus-mcp: Skill for Claude Code

.agents/skills/globus-feature/SKILL.md

globus-feature is a skill for Claude Code from PurdueRCAC/globus-mcp. It costs 135 tokens per session (3,703 once invoked), scanned A, original, MIT.

A workflow for starting a new feature, fix, or refactor in the Globus MCP project. It checks that the main branch is clean, creates a work branch, and turns a prompt or issue into a bounded goal document with acceptance conditions.

In plain words
What is it for?
Use it to begin a Globus MCP change from a clean main branch, create the appropriate feature or fix branch, defer an issue, and produce a reviewed specification in spec/{slug}/GOAL.md.
Why use it?
It helps define what a change should accomplish before detailed planning or implementation begins, while recording what is out of scope.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions Claude Code; installed under .agents/ (shared by several agents).

This is PurdueRCAC/globus-mcp's own configuration. It tells Claude Code how to work on globus-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything globus-mcp configures →

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-feature/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.

agentmods badge for globus-feature

README.md
[![agentmods](https://agentmods.dev/badge/skills/purduercac/globus-mcp/globus-feature/github.svg)](https://agentmods.dev/skills/purduercac/globus-mcp/globus-feature)
Your own site
<a href="https://agentmods.dev/skills/purduercac/globus-mcp/globus-feature"><img src="https://agentmods.dev/badge/skills/purduercac/globus-mcp/globus-feature/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.

agentmods 80×15 button for globus-feature

Your own site · 80×15
<a href="https://agentmods.dev/skills/purduercac/globus-mcp/globus-feature"><img src="https://agentmods.dev/badge/skills/purduercac/globus-mcp/globus-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,703 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00135 $0.03703
Opus 5 $0.00068 $0.01852
Sonnet 5 $0.00027 $0.00741
Haiku 4.5 $0.00014 $0.00370

Measured 9d ago against content hash f86bb07e2fb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

globus-feature 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-feature/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

globus-feature — shape the goal

When to Use

Invoke /globus-feature on a clean main to begin a new unit of work. It produces exactly one artifact — a refined spec/{slug}/GOAL.md on a fresh branch — and stops for your sign-off before the expensive /globus-plan step. This is shaping, in the Shape Up sense: make the goal coherent, bounded, and unambiguous, but leave design freedom for the plan. Do not research or read a lot of code here.

Reference (load only if needed): .agents/factory/methodology.md, .agents/factory/ears.md, the template .agents/factory/templates/GOAL.md.

Harness portability. These skills run on any harness, not only Claude Code — see factory/portability.md. Here the Claude-specific affordances degrade gracefully: if the Current state block below isn't auto-injected, run those commands yourself in Step 1; if AskUserQuestion is unavailable, ask in plain text and STOP. Everything else (git) 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
  • Untracked GOAL.md files: !git ls-files --others --exclude-standard 'spec/**/GOAL.md'
  • Open issues: !git ls-files 'issues/*.md'

Argument Parsing

Parse $ARGUMENTS case-insensitively. If self-contradictory, STOP and ask.

  • A path matching spec/<slug>/GOAL.mdadopt that file as the seed; {slug} is taken from the path. (This is the "I hand-wrote a GOAL.md" flow.)
  • A path matching issues/<slug>.md (or .security/issues/<slug>.md) → promote that issue. {slug} is the file stem; its frontmatter supplies kind and appetite unless the invocation overrides them. A bare {slug} naming an existing issues/{slug}.md resolves the same way. See "Promoting an issue" in Step 4.
  • fix / bug / refactor → set kind; otherwise infer from the wording, defaulting to feature.
  • appetite small / appetite big → set appetite; else default small for kind: fix, big for feature/refactor. Those two values are the whole vocabulary; a seed whose frontmatter still reads medium rounds up to big, because rounding up costs a research fan-out while rounding down fails globus-review's scope check against a contract a human already accepted. Record the round-up as a dated Clarification in the GOAL; leave the seed's own frontmatter alone.
  • Everything else → the inline feature description (the seed prompt).
  • No arguments and no untracked spec/*/GOAL.md present → STOP and ask for a description or a GOAL.md path.

Read the full file on GitHub · 224 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.

  1. 9d ago First seen · 224 lines · 135 tokens per session scan A f86bb07e2fb4

Subscribe to this mod's changes

globus-feature is a skill published in the GitHub repository PurdueRCAC/globus-mcp (1 stars, last pushed 14d ago), licensed MIT. It adds 135 tokens to every session and 3,703 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens

nvca-chart-release

Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.

NVIDIA/nvcf · 61 tokens