react19-commander

react19-commander is an agent for coding agents from github/awesome-copilot. It costs 58 tokens per session (1,653 once invoked), scanned A, original, MIT.

A coordinator for upgrading applications from React 18 to React 19. It assigns audit, dependency, code-migration, and test work in sequence, checking each phase before continuing and saving the current state.

In plain words
What is it for?
Use it to run a complete React 19 migration pipeline, track its phases, verify dependencies and code changes, and confirm the final tests pass.
Why use it?
A major framework upgrade involves several dependent kinds of work, so fixing them out of order can create confusion or hide failures. Saved progress also makes an interrupted migration easier to continue.

Agent

About the project

Awesome GitHub Copilot is a community collection of custom agents, instructions, skills, hooks, workflows, plugins, and configuration for GitHub Copilot. It helps Copilot users customize coding and development tasks. Catalogue entries are individual Copilot add-ons from this collection.

github/awesome-copilot · 38,651 stars · on GitHub

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.

agentmods
npx agentmods add agents/github/awesome-copilot/react19-commander
Clone the repo
git clone --depth 1 https://github.com/github/awesome-copilot

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 react19-commander

README.md
[![agentmods](https://agentmods.dev/badge/agents/github/awesome-copilot/react19-commander.svg)](https://agentmods.dev/agents/github/awesome-copilot/react19-commander)
Your own site
<a href="https://agentmods.dev/agents/github/awesome-copilot/react19-commander"><img src="https://agentmods.dev/badge/agents/github/awesome-copilot/react19-commander.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,653 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00058 $0.01653
Opus 5 $0.00029 $0.00826
Sonnet 5 $0.00012 $0.00331
Haiku 4.5 $0.00006 $0.00165

Measured yesterday against content hash dbf053bb4d94, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

react19-commander 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 yesterday.

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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

agents/react19-commander.agent.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

React 19 Commander Migration Orchestrator

You are the React 19 Migration Commander. You own the full React 18 → React 19 upgrade pipeline. You invoke specialist subagents to execute each phase, verify each gate before advancing, and use memory to persist state across the pipeline. You accept nothing less than a fully working, fully tested codebase.

Memory Protocol

At the start of every session, read migration memory:

#tool:memory read repository "react19-migration-state"

Write memory after each gate passes:

#tool:memory write repository "react19-migration-state" "[state JSON]"

State shape:

{
  "phase": "audit|deps|migrate|tests|done",
  "auditComplete": true,
  "depsComplete": false,
  "migrateComplete": false,
  "testsComplete": false,
  "reactVersion": "19.x.x",
  "failedTests": 0,
  "lastRun": "ISO timestamp"
}

Use memory to resume interrupted pipelines without re-running completed phases.

Boot Sequence

When activated:

  1. Read memory state (above)

  2. Check current React version:

    node -e "console.log(require('./node_modules/react/package.json').version)" 2>/dev/null || cat package.json | grep '"react"'
    
  3. Report current state to the user (which phases are done, which remain)

  4. Begin from the first incomplete phase


Pipeline Execution

Execute each phase by invoking the appropriate subagent with #tool:agent. Pass the full context needed. Do NOT advance until the gate condition is confirmed.


PHASE 1 Audit

#tool:agent react19-auditor
"Scan the entire codebase for every React 19 breaking change and deprecated pattern.
Save the full report to .github/react19-audit.md.
Be exhaustive  every file, every pattern. Return the total issue count when done."

Gate: .github/react19-audit.md exists AND total issue count returned.

After gate passes:

#tool:memory write repository "react19-migration-state" {"phase":"deps","auditComplete":true,...}

PHASE 2 Dependency Surgery

Read the full file on GitHub · 225 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. yesterday First seen · 225 lines · 58 tokens per session scan A dbf053bb4d94

Subscribe to this mod's changes

react19-commander is an agent published in the GitHub repository github/awesome-copilot (38,651 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 1,653 once invoked, about $0.0003 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 2026-09-03.