What is package-update?

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

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

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.

package-update — Skill for Claude Code and Codex by Vladick-Pick

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.

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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00030	$0.02179
Opus 5.5	$0.00012	$0.00872
Sonnet 5.5	$0.00006	$0.00436
Haiku 4.5	$0.00003	$0.00218

Measured 2mo ago against content hash b15958b8861b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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.

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

Run:

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

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.
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.

On approval, run:

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

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.

2mo 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 (3 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 2,179 once invoked, about $0.0001 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.

DevOps and cloud agent-evals agent-skills ai-agents business-ontology codex ontology

package-update next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
package-updateVladick-Pick/business-ontology	Skill	3	3mo ago	MIT	A	30	Claude Code, Codex
graph-mutation-planpotpie-ai/potpie	Skill	5.8k	8d ago	Apache-2.0	A	22	Claude Code, Codex
open-ontologiesfabio-rovai/open-ontologies	Skill	2.8k	2d ago	MIT	A	109	Claude Code
ontology-engineeringfabio-rovai/open-ontologies	Skill	2.8k	2d ago	MIT	A	47	Claude Code
basic-skilldarkrishabh/agent-skills-eval	Skill	811	2d ago	MIT	A	17	Claude Code, Codex
Rare Disease Skills Indexaristoteleo/PantheonOS	Skill	493	yesterday	BSD-2-Clause	A	43	Claude Code, Codex
objectstack-aiobjectstack-ai/objectstack	Skill	83	yesterday	Apache-2.0	A	112	Claude Code, Codex