orbit-upgrade

orbit-upgrade is a skill for Claude Code from Abdulaziz-almoshen/orbit. It costs 71 tokens per session (2,442 once invoked), scanned D, original, MIT.

An upgrade command for the Orbit plugin, which runs agent work in a repeating loop. It gets the newest version from GitHub and reports what changed.

In plain words
What is it for?
Use it to upgrade Orbit, update an agent loop, or inspect whether a newer version is available.
Why use it?
It removes the need to find the installed plugin, check its version, and update it by hand. It also avoids overwriting project files that Orbit previously created.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the orbit plugin — 2 skills, 1 command shipped together

Good fit Use it to upgrade Orbit, update an agent loop, or inspect whether a newer version is available.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Abdulaziz-almoshen/orbit
Claude Code
/plugin install orbit

Made for: Claude Code.

Or install orbit, the plugin that ships this one along with the rest of its 2 skills, 1 command.

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 orbit-upgrade

README.md
[![agentmods](https://agentmods.dev/badge/skills/abdulaziz-almoshen/orbit/orbit-upgrade/github.svg)](https://agentmods.dev/skills/abdulaziz-almoshen/orbit/orbit-upgrade)
Your own site
<a href="https://agentmods.dev/skills/abdulaziz-almoshen/orbit/orbit-upgrade"><img src="https://agentmods.dev/badge/skills/abdulaziz-almoshen/orbit/orbit-upgrade/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 orbit-upgrade

Your own site · 80×15
<a href="https://agentmods.dev/skills/abdulaziz-almoshen/orbit/orbit-upgrade"><img src="https://agentmods.dev/badge/skills/abdulaziz-almoshen/orbit/orbit-upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,442 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 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 $0.00071 $0.02442
Opus 5 $0.00036 $0.01221
Sonnet 5 $0.00014 $0.00488
Haiku 4.5 $0.00007 $0.00244

Measured 12d ago against content hash 25dbbcc6ecac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade D, and why

orbit-upgrade scanned grade D with 3 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 12d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

ORBIT_BRANCH="$_BR" bash -c 'curl -fsSL "https://raw.githubusercontent.com/Abdulaziz-almoshen/orbit/'"$_BR"'/install.sh" | bash'

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

**Skills-dir install (`IS_GIT=no` and `$INSTALL_DIR/.install-method` says `method=skills-dir`, or `$INSTALL_DIR` is under `~/.claude/skills/`) — the default install:** re-run the installer, which re-downloads the latest

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

ORBIT_BRANCH="$_BR" bash -c 'curl -fsSL "https://raw.githubusercontent.com/Abdulaziz-almoshen/orbit/'"$_BR"'/install.sh" | bash'
orbit-upgrade/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/orbit-upgrade

Upgrade the orbit plugin and show what's new. This updates the plugin/scaffolder only — it never touches the CLAUDE.md, roles, or loop files a previous run already scaffolded into a product repo (those are that project's files).

Inline upgrade flow

This section is referenced by the /orbit preamble when it detects UPGRADE_AVAILABLE <old> <new>. Run the steps in order.

Step 0: resolve the install (one deterministic call — no candidate loop)

Run the trusted resolver. It ALWAYS names the active install (it runs from it), and reports version, commit, how many commits behind origin, dirty tracked files, and any stale copies — so there is no narrated search and no "standard paths didn't resolve." The executable is literal (./orbit-resolve), the variable is only a cd argument — same style as the /orbit preamble, so the guard never prompts.

_CC="${CLAUDE_CONFIG_DIR:-$HOME/.claude}"
if   [ -n "${CLAUDE_PLUGIN_ROOT:-}" ] && [ -x "$CLAUDE_PLUGIN_ROOT/bin/orbit-resolve" ]; then ( cd "$CLAUDE_PLUGIN_ROOT/bin" && ./orbit-resolve --upgrade-check )
elif [ -x "$_CC/skills/orbit/bin/orbit-resolve" ];          then ( cd "$_CC/skills/orbit/bin" && ./orbit-resolve --upgrade-check )
elif [ -x "$HOME/.claude/skills/orbit/bin/orbit-resolve" ]; then ( cd "$HOME/.claude/skills/orbit/bin" && ./orbit-resolve --upgrade-check )
elif [ -x ".claude/skills/orbit/bin/orbit-resolve" ];       then ( cd .claude/skills/orbit/bin && ./orbit-resolve --upgrade-check )
fi

Read the JSON it prints:

  • active_installINSTALL_DIR for the rest of these steps; is_gitIS_GIT.
  • behind > 0 → an upgrade is available (proceed). behind == 0 → already current (tell the user the version and stop, unless they explicitly asked to re-pull).
  • dirty == true → mention dirty_files before Step 3 (they'll be stashed).
  • other_installs non-empty → note the stale copy (e.g. an old plugin-cache …/orbit/orbit/0.4.0) so the user can remove it; it is NOT the active install and won't be touched.

Read the full file on GitHub · 173 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. 12d ago First seen · 173 lines · 71 tokens per session scan D 25dbbcc6ecac

Subscribe to this mod's changes

orbit-upgrade is a skill published in the GitHub repository Abdulaziz-almoshen/orbit (4 stars, last pushed 22d ago), licensed MIT. It adds 71 tokens to every session and 2,442 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, enumerates other installed skills, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.