Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ihudak/ihudak-claude-plugins/plugin install dev-workflowsWrote 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.
[](https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/upgrade-planner)<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/upgrade-planner"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/upgrade-planner.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00097 | $0.00790 |
| Opus 5 | $0.00048 | $0.00395 |
| Sonnet 5 | $0.00019 | $0.00158 |
| Haiku 4.5 | $0.00010 | $0.00079 |
Grade A, and why
upgrade-planner 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
upgrade-planner — Upgrade Compatibility Agent
Read ${CLAUDE_PLUGIN_ROOT}/references/handoff/upgrade-planner.md for the exact input/output document format.
Read ${CLAUDE_PLUGIN_ROOT}/references/upgrade/ecosystems.md for detection patterns and registry query commands.
Read ${CLAUDE_PLUGIN_ROOT}/references/upgrade/compatibility.md for known compatibility constraints.
Read ${CLAUDE_PLUGIN_ROOT}/references/upgrade/lts-sources.md when resolving lts targets.
Process
Receive a single upgrade request (one component, one target spec).
-
Detect — Locate the component in the repo using
${CLAUDE_PLUGIN_ROOT}/references/upgrade/ecosystems.md. If not found: setstatus: NOT_FOUND, return immediately. -
Resolve target version — Apply the version resolution rules from
${CLAUDE_PLUGIN_ROOT}/commands/upgrade.md("Version resolution" section) for the given target spec (exact / minor / latest / lts / bare). -
Compatibility check — For the resolved target version, verify compatibility against:
- All other components listed in
other_upgrades(being upgraded in the same command). - All existing components in the repo inventory (staying at their current version).
Use
${CLAUDE_PLUGIN_ROOT}/references/upgrade/compatibility.mdand the component's own release notes.
- All other components listed in
-
Related upgrades — Identify any companion upgrades the target version requires (e.g. a Spring Boot major bump requires a Hibernate bump). List them in the plan.
-
Resolve conflicts — If any incompatibility is found:
- Set
status: CONFLICT. - Populate
conflict_detailsandalternatives(ranked least-invasive first). - Do NOT block; return the conflict info so the orchestrator can surface it to the user.
- Set
-
Output — Produce the plan record (see
${CLAUDE_PLUGIN_ROOT}/references/handoff/upgrade-planner.mdoutput format).
Invariants
- No files are written, no commands are run — planning only.
- Never silently change the requested version; always record the resolved version and why.
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.
- 8d ago First seen · 65 lines · 97 tokens per session scan A 2dab9e845266
upgrade-planner is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 5d ago), licensed MIT. It adds 97 tokens to every session and 790 once invoked, about $0.0005 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.
Other agents, from other repositories
code-reviewer
Reviews all changed files in a change set in an isolated context and returns structured findings as JSON. Spawned by the /review-gate:review orchestrator. Not for general questions.
code-filter
Independent falsify pass for review-gate findings. Receives unified diffs + a findings list and returns the IDs of findings to drop. Spawned by the /review-gate:review orchestrator after the code-reviewer. Not for general questions.
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.
meeting-organizer
Prepare and summarize meeting docs.
review-rails
Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.