agentmods.dev

aips-upgrade

A command that updates the global AIPS plugin marketplace, the AIPS plugin, and its installed dependency plugins.

In plain words
What is it for?
Use it to refresh marketplace data, upgrade plugin versions, report what changed, and restart the agent-memory service when required.
Why use it?
It keeps the shared plugin setup current without changing the settings of an individual project.

Command

Part of the AIPS plugin — 11 commands, 4 agents shipped together

5 3mo ago B scan 15 tokens original MIT
View the source file kernalix7/AIPS
Install

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.

agentmods
npx agentmods add commands/kernalix7/aips/aips-upgrade
Clone the repo
git clone --depth 1 https://github.com/kernalix7/AIPS

Or install AIPS, the plugin that ships this one along with the rest of its 11 commands, 4 agents.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,565 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00015 $0.01565
Opus 5 $0.00008 $0.00783
Sonnet 5 $0.00003 $0.00313
Haiku 4.5 $0.00002 $0.00156

Measured 2d ago against content hash 7c5754e9367f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

aips-upgrade scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

UPGRADE_SH="$(find ~/.claude/plugins/cache/AIPS/AIPS/lib -name upgrade.sh 2>/dev/null | head -1)"
commands/aips-upgrade.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/aips:upgrade

Refresh everything global: plugin marketplace metadata, the AIPS plugin, and every dependency plugin AIPS relies on. Per-project state is not touched — run /aips:update afterward to sync the local project.

What it does

  1. Marketplace refresh: 
    claude --print "/plugin marketplace update"
  2. AIPS plugin upgrade: 
    claude --print "/plugin update AIPS@AIPS"
    Capture pre/post versions from ~/.claude/plugins/AIPS/.claude-plugin/plugin.json.
  3. Dependency plugins — for each of agentmemory, caveman, rtk, codex-plugin-cc (when present): 
    claude --print "/plugin update <name>@<marketplace>"
    Capture pre/post versions from each plugin's plugin.json.
  4. Restart agentmemory service if its version changed (Linux): 
    systemctl --user restart agentmemory
    macOS: launchctl kickstart -k gui/$(id -u)/agentmemory (if loaded). Other platforms: WARN and skip.

Output

One line per plugin showing the version delta:

[upgrade] marketplace        refreshed
[upgrade] AIPS               v6.0.0 → v6.1.0
[upgrade] agentmemory        v0.3.2 → v0.3.3
[upgrade] caveman           v1.1.0 (no change)
[upgrade] rtk                v2.0.1 → v2.0.2
[upgrade] codex-plugin-cc        not installed
[upgrade] agentmemory svc    restarted (version changed)
note: run /aips:update inside each project to sync per-project files.

Rules

  • Globals only. Never touch .priv-storage/, root symlinks, project source.
  • If marketplace refresh fails, abort before running any plugin update.
  • Surface any plugin update failure individually; do not abort the whole batch on one failure.

Optional arg: --to v7.0 (hybrid migration)

When invoked as /aips:upgrade --to v7.0 (or /aips:upgrade --to v7.0 $ARGUMENTS), perform the v6.0 → v7.0 hybrid migration for the current project instead of (or in addition to) the global plugin refresh.

Detection

  1. Read .priv-storage/.aips-version in the project root.
    • If missing and .priv-storage/CLAUDE.md is present with the v6.0 section layout (Sections 1–7, 11) → treat as v6.0.
    • If file reads 7.0 → abort with already on v7.0 (no-op).
    • If file reads anything else (e.g. 5.x) → abort with unsupported source version: <ver>; run /aips:migrate-from-md first.

Read the full file on GitHub · 130 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. 2d ago First seen · 130 lines · 15 tokens per session scan B 7c5754e9367f

Subscribe to this mod's changes

aips-upgrade is a command published in the GitHub repository kernalix7/AIPS (5 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 1,565 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other commands, from other repositories

git

Git operations with intelligent commit messages and workflow optimization.

SuperClaude-Org/SuperClaude_Framework · 11 tokens

checklist

Generate a custom checklist for the current feature based on user requirements.

github/spec-kit · 13 tokens

clarify

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

github/spec-kit · 27 tokens

specify

Create or update the feature specification from a natural language feature description.

github/spec-kit · 13 tokens

analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

github/spec-kit · 26 tokens

converge

Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.

github/spec-kit · 35 tokens