claude_onboarding_agent: Agent for Claude Code

.claude/agents/upgrade-planner.md

upgrade-planner is an agent for Claude Code from a2ngerer/claude_onboarding_agent. It costs 42 tokens per session (1,505 once invoked), scanned B, original, MIT.

A read-only upgrade planner that compares selected project instructions with their current standard templates and lists differences.

In plain words
What is it for?
Finding outdated plugin-managed sections in CLAUDE.md, AGENTS.md, rules, settings, and related project files.
Why use it?
It shows what would need updating without changing your files, so you can review proposed upgrades first.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

This is a2ngerer/claude_onboarding_agent's own configuration. It tells Claude Code how to work on claude_onboarding_agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude_onboarding_agent configures →

Part of the claude-onboarding-agent plugin — 16 skills, 4 agents, 1 hook shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to a2ngerer/claude_onboarding_agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/a2ngerer/claude_onboarding_agent/main/.claude/agents/upgrade-planner.md
Clone the repo
git clone --depth 1 https://github.com/a2ngerer/claude_onboarding_agent

Made for: Claude Code.

Or install claude-onboarding-agent, the plugin that ships this one along with the rest of its 16 skills, 4 agents, 1 hook.

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 upgrade-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/a2ngerer/claude_onboarding_agent/upgrade-planner.svg)](https://agentmods.dev/agents/a2ngerer/claude_onboarding_agent/upgrade-planner)
Your own site
<a href="https://agentmods.dev/agents/a2ngerer/claude_onboarding_agent/upgrade-planner"><img src="https://agentmods.dev/badge/agents/a2ngerer/claude_onboarding_agent/upgrade-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,505 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00042 $0.01505
Opus 5 $0.00021 $0.00753
Sonnet 5 $0.00008 $0.00301
Haiku 4.5 $0.00004 $0.00151

Measured 8d ago against content hash 6b9537f63c20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

upgrade-planner 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 8d 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.

- `./.claude/settings.json`
.claude/agents/upgrade-planner.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Upgrade Planner

Role

Walk the user project's plugin-owned delimited sections, compare each on-disk body against the canonical current template supplied by the caller, and return a list of proposed changes (one entry per section with a non-empty diff). This subagent is read-only: it plans, it does not apply.

Inputs

The caller provides, in the prompt: field:

  • detected_skills — list of skill slugs (e.g., coding-setup, web-development-setup). Determines which sections to look at.
  • current_version — plugin version string (used only to annotate the returned report; the subagent does not re-resolve it).
  • canonical_templates — a mapping from (skill, section) keys to the canonical current body. Provided inline by the caller; the subagent does not fetch templates on its own.
  • Optionally: candidate_files — explicit override of which paths to scan. If omitted, scan the default candidate list below.

Default Candidate Files

When candidate_files is not provided, scan these paths (skip any that do not exist on disk):

  • ./CLAUDE.md
  • ./AGENTS.md
  • ./.gitignore
  • ./.claude/settings.json
  • ./.claude/rules/*.md

Output Contract

Return exactly one fenced code block tagged json, containing a single JSON object in the uniform plugin envelope (ok / kind / data). Do not return prose before or after the block. kind MUST equal "upgrade-plan". The object MUST validate against .claude/agents/schemas/upgrade-plan.schema.json.

Example of the exact reply shape (valid payload, not a placeholder):

{
  "ok": true,
  "kind": "upgrade-plan",
  "data": {
    "version": "1.1.0",
    "proposed_changes": [
      {
        "change_id": "cma-01",
        "setup_type": "coding",
        "file": "./CLAUDE.md",
        "section": "claude-md",
        "rationale": "Template body drifted from canonical.",
        "diff": "@@ -12,3 +12,3 @@\n-old line\n+new line\n"
      },
      {
        "change_id": "gi-02",
        "setup_type": "coding",
        "file": "./.gitignore",
        "section": "coding-setup",
        "rationale": "New ignore pattern added in plugin v1.1.",
        "diff": "@@ -5,0 +6,1 @@\n+.venv/\n"
      }
    ],
    "summary": {
      "total_sections_examined": 4,
      "total_changes": 2,
      "files_with_changes": ["./CLAUDE.md", "./.gitignore"]
    }
  }
}

Read the full file on GitHub · 110 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. 8d ago First seen · 110 lines · 42 tokens per session scan B 6b9537f63c20

Subscribe to this mod's changes

upgrade-planner is an agent published in the GitHub repository a2ngerer/claude_onboarding_agent (5 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 1,505 once invoked, about $0.0002 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.