agentic-upgrade

agentic-upgrade is a skill for Claude Code from Jarroslav/agentic-os. It costs 134 tokens per session (5,215 once invoked), scanned A, original, Apache-2.0.

An updater for a repository's scaffolded agentic-os layer, which is a generated set of agent instructions and automation files. It compares the old installed files with newer templates and the user's changes.

In plain words
What is it for?
It helps upgrade the scaffold, reconcile changed files, replace managed sections, and offer regeneration of generated agents while preserving adopted files and unknown settings.
Why use it?
It prevents user edits from being overwritten silently during an upgrade. Unchanged managed files can be updated, while modified files are identified for review.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Part of the agentic-os plugin — 4 skills shipped together

Good fit It helps upgrade the scaffold, reconcile changed files, replace managed sections, and offer regeneration of generated agents while preserving adopted files and unknown settings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jarroslav/agentic-os/agentic-upgrade
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.

Any agent
npx skills add Jarroslav/agentic-os --skill agentic-upgrade
Clone the repo
git clone --depth 1 https://github.com/Jarroslav/agentic-os

Made for: Claude Code.

Or install agentic-os, the plugin that ships this one along with the rest of its 4 skills.

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 agentic-upgrade

README.md
[![agentmods](https://agentmods.dev/badge/skills/jarroslav/agentic-os/agentic-upgrade.svg)](https://agentmods.dev/skills/jarroslav/agentic-os/agentic-upgrade)
Your own site
<a href="https://agentmods.dev/skills/jarroslav/agentic-os/agentic-upgrade"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/agentic-upgrade.svg" alt="Measured on agentmods" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,215 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 $0.00134 $0.05215
Opus 5 $0.00067 $0.02608
Sonnet 5 $0.00027 $0.01043
Haiku 4.5 $0.00013 $0.00522

Measured 6d ago against content hash 464715ede657, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agentic-upgrade 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 6d 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.

plugins/agentic-os/skills/agentic-upgrade/SKILL.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentic-upgrade — scaffold updater

You reconcile the target repo's scaffold with the newer plugin templates. The install journal is the third point of the three-way merge: it records what agentic-os last wrote (sha256), from which template (template), and who owns the file now (owner). Never overwrite silently — every destructive choice is either provably safe (hash-identical to what we wrote) or user-confirmed.

Conventions (PLUGIN, TARGET, journal shape, rendering rules incl. the .json.tmpl quoted-array and newline-list conventions) are identical to skills/agentic-init/SKILL.md — read its "Conventions" section first. Like init: never git add/git commit in the target repo.

When journal.adoption.mode == "adopt-existing", resolve canonical agents, skills and state from journal.adoption and never fall back to hardcoded .agentic/ paths. Entries with origin: "adopted-existing" are immutable: you may verify them and report drift, but never render, replace, regenerate, re-synthesize or delete them — and that covers Codex TOML adapters, hook registrations and rules as much as agent contracts. Preserve Codex configuration keys you do not recognise; an upgrade that drops a key it did not write is indistinguishable from corruption.

Phase 1 — Version gate

  1. Read TARGET/.agentic/agentic-os/install.json. Missing ⇒ stop: "no install journal — run /agentic-init".
  2. NEW = "version" from PLUGIN/.claude-plugin/plugin.json; OLD = journal.agentic_os_version.
  3. NEW == OLD ⇒ nothing to upgrade; offer a refresh (Phase 2 with unchanged-only rules) or just /agentic-doctor, then stop. NEW < OLD ⇒ stop and escalate (plugin downgraded — human decision).
  4. Re-load journal.answers — every re-render uses the journaled answers; the upgrade never re-interviews (changing answers is an /agentic-init re-run).

Phase 2 — Per-file three-way reconciliation

For every journal entry with a template ID (the destination map lives in skills/agentic-init/SKILL.md Phase 4), compute: RECORDED = journaled sha256, CURRENT = sha256 of the file on disk, NEWRENDER = the NEW template rendered with journal.answers (including init's installer-side conditionals: the warn-only git-sync patch when answers.git_sync_mode is warn-only, migration-notice skip on empty migrations dir, registry row pruning). Entries with template: "derived" have no template to render — handle them in the derived branch below, never via a template diff.

Read the full file on GitHub · 327 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 327 lines · 0 tokens per session scan A 464715ede657

Subscribe to this mod's changes

agentic-upgrade is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 134 tokens to every session and 5,215 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens