What is globus-build?

A workflow for continuing a planned globus-mcp feature or fix one phase at a time. It reads the project's technical plan and progress state, implements the next phase, verifies it, and records the result.

Use it on a feature or fix branch with a TECH.md plan to resume work, run the required checks, update progress, and commit the code and state together.

It removes the need to re-explain a feature's design and helps keep implementation progress aligned with the approved plan.

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-build/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-build/github.svg)](https://agentmods.dev/skills/purduercac/globus-mcp/globus-build)

Your own site

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

Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,956 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	$0.00114	$0.03956
Opus 5.5	$0.00046	$0.01582
Sonnet 5.5	$0.00023	$0.00791
Haiku 4.5	$0.00011	$0.00396

Measured 2mo ago against content hash 260d4dea2450, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

globus-build 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 2mo 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-build/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

globus-build — execute the roadmap (resume-and-implement)

When to Use

Invoke /globus-build on a feature/fix branch whose spec/{slug}/TECH.md exists, to execute the next slice of the roadmap without re-explaining the project. The rhythm is one-phase-then-stop: scale up with arguments when you trust the next chunk, scale down to a dry run when you don't. TECH.md frontmatter is the resume ground-truth; PLAN.md is the authoritative design; GOAL.md R-IDs are the locked contract; research/ holds detail. Track progress only in TECH.md (via the scripts).

Reference: methodology.md, invariants.md, and AGENTS.md (the constitution).

Harness portability. Runs on any harness — see factory/portability.md. Fallback: if the Current state block isn't auto-injected, run those commands yourself in Step 1 (which already re-runs next_phase.py). No other Claude-specific affordances — the rest 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
Commits on branch (vs main): !git log --oneline main..HEAD 2>/dev/null | head -n 15
FSM: resolved in Step 1 by running uv run python .agents/factory/bin/next_phase.py spec/{slug}/TECH.md (a load-time injection can't strip the branch prefix to form {slug}).

Argument Parsing

Parse $ARGUMENTS case-insensitively; if ambiguous, STOP and ask.

status / report → summarize FSM state (via next_phase.py, Step 1) + last commit; no work.
dry run / plan only / preview → identify the target phase and load context, but make no edits/commits — report the plan (checklist items, files, verify command, expected commit).
phase P<n> / at P<n> → execute that phase regardless of current_phase.
through P<n> / up to P<n> → execute forward, stopping after P<n> completes.
next N / N phases → execute the next N incomplete phases (each its own commit).
bundle → collapse the run into a single commit (only for tightly-coupled phases).
no-pause → continue past the natural phase-boundary stop (use sparingly).
No arguments → default next-phase-then-stop.

Read the full file on GitHub · 228 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.

2mo ago First seen · 228 lines · 114 tokens per session scan A 260d4dea2450

Subscribe to this mod's changes

globus-build is a skill published in the GitHub repository PurdueRCAC/globus-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 114 tokens to every session and 3,956 once invoked, about $0.0005 per session on Opus 5.5. 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

globus-build next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
globus-buildPurdueRCAC/globus-mcp	Skill	2	2mo ago	MIT	A	114	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

globus-mcp: Skill for Claude Code