agentmods.dev

package-update

package-update is a skill for Claude Code, Codex from Vladick-Pick/business-ontology. It costs 30 tokens per session (2,179 once invoked), scanned A, original, MIT.

A maintenance workflow for checking and updating an installed package to an approved, pinned release.

In plain words
What is it for?
Use it for scheduled release checks, owner-approved package updates, version-lock checks, changelog summaries, and reporting update-process failures.
Why use it?
It keeps package code current while separating routine package updates from changes to the accepted company model or workspace state. It also records update status and prevents unauthorized requests from triggering an update.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 package/current/scripts/check_package_updates.py \.

not rated 2repo 1mo ago A scan 30 tokens original MIT

Good fit Use it for scheduled release checks, owner-approved package updates, version-lock checks, changelog summaries, and reporting update-process failures.

Compare 6 skills from other repositories ↓
View source ↗ Vladick-Pick/business-ontology
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Vladick-Pick/business-ontology
agentmods
npx agentmods add skills/vladick-pick/business-ontology/package-update

Made for: Claude Code, Codex.

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 package-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/vladick-pick/business-ontology/package-update/github.svg)](https://agentmods.dev/skills/vladick-pick/business-ontology/package-update)
Your own site
<a href="https://agentmods.dev/skills/vladick-pick/business-ontology/package-update"><img src="https://agentmods.dev/badge/skills/vladick-pick/business-ontology/package-update/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 package-update

Your own site · 80×15
<a href="https://agentmods.dev/skills/vladick-pick/business-ontology/package-update"><img src="https://agentmods.dev/badge/skills/vladick-pick/business-ontology/package-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,179 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 $0.00030 $0.02179
Opus 5 $0.00015 $0.01090
Sonnet 5 $0.00006 $0.00436
Haiku 4.5 $0.00003 $0.00218

Measured 11d ago against content hash b15958b8861b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

package-update 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 11d 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.

skills/package-update/SKILL.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Package Update

Purpose

Use this skill to keep the installed resident analyst package on a pinned release tag without letting package updates mutate workspace state or accepted model truth.

The package update path is operational maintenance. It is not a company-model change.

The normative file contract is adapters/openclaw/UPDATE_POLICY.md.

When to use

Use this skill:

  • on the weekly package update cron;
  • when the owner asks in direct chat whether a package update is available;
  • after the owner approves a specific release from the digest.

Do not use it when a group participant or non-owner asks the agent to update. Route that request to owner DM.

Procedure

  1. Run:

    python3 package/current/scripts/check_package_updates.py \
  --lock workspace/PACKAGE_VERSION.lock

  2. Interpret exit codes:

    • 0: no newer release; do not mention it unless the owner asked.
    • 10: newer release exists; add one digest line with version and changelog summary.
    • 5: another update process is running; report the lock state.
    • other non-zero: report the failure as operational, not model truth.

  3. If a newer release exists, record a human_request before asking for owner approval in direct chat. Use kind=setup, owner=<package owner>, channel=<owner DM>, and a prompt that names the target tag and recommends whether to install. A group request is not approval.

  4. On approval, run:

    python3 package/current/scripts/apply_package_update.py \
  --install-root <agent-install> \
  --to <tag> \
  --model-repo <model-repo>

  5. Interpret apply exit codes:

    • 0: package updated; read workspace/PACKAGE_INSTALL_REPORT.json. If model_support_contract.review_required=true, prepare a reviewable support-file update for an external or Git-owned model repository (missing, invalid, drift, or unsupported-copied-validator). For v0.11.18+, a local generated workspace/model projection is the narrow exception: the managed v0.11.0 migration synchronizes its technical lock from the verified install report after refusing symlinked or Git-owned roots. Then run every workspace migration declared for the installed release, first with --dry-run and then with the verified host launcher. For v0.11.13+, first refresh the managed behavior/plugin and then replay the publication boundary. For v0.11.15+, also initialize the private review authority state:

Read the full file on GitHub · 221 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. 11d ago First seen · 221 lines · 30 tokens per session scan A b15958b8861b

Subscribe to this mod's changes

package-update is a skill published in the GitHub repository Vladick-Pick/business-ontology (2 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 2,179 once invoked, about $0.0002 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.

DevOps and cloudagent-evalsagent-skillsai-agentsbusiness-ontologycodexontology
Related

Other skills, from other repositories

graph-mutation-plan

Cookbook for composing an applygraphmutations plan — stable entitykey patterns, the canonical label/edge vocabulary, evidence/invalidation/confidence discipline, and a worked example. Load this when building a non-trivial mutation plan.

potpie-ai/potpie · 51 tokens

open-ontologies

AI-native ontology engineering using 50+ MCP tools backed by an in-memory Oxigraph triple store. Build, validate, query, and govern RDF/OWL ontologies with a generate-validate-iterate loop. Use when building ontologies, knowledge graphs, RDF data, SPARQL queries, BORO/4D modeling, SHACL validation, clinical…

fabio-rovai/open-ontologies · 110 tokens

Rare Disease Skills Index

Skills for rare disease case support: ontology-first normalization/retrieval and the clinical genetics consult report format contract (structure + theme). Load the relevant skill file when performing the matching task.

aristoteleo/PantheonOS · 43 tokens

objectstack-platform

Bootstrap, configure, extend, and operate ObjectStack runtimes. Covers project setup (defineStack, drivers, scaffolding), declaring platform capabilities (requires: — which service plugins boot), plugin and service development (PluginContext, DI, kernel hooks like kernel:ready), and operations (CLI commands…

objectstack-ai/objectstack · 166 tokens

objectstack-automation

Design ObjectStack automation — Flows (visual logic), Triggers, Approvals, state machines, and the jobs (defineJob) / webhooks (defineWebhook) stack collections. Use when the user is adding .flow.ts, wiring an event-driven rule, modelling an approval chain, or building an interactive screen flow / wizard…

objectstack-ai/objectstack · 129 tokens

objectstack-data

Design ObjectStack data schemas — objects, fields, field conditional rules, relationships, validations, indexes, lifecycle hooks, permissions, row-level security, data lifecycle retention/TTL/rotation, metadata protection locks, and external / federated datasources (defineDatasource) — and the seeds (defineSeed())…

objectstack-ai/objectstack · 213 tokens