react-sentinel-runtime-debugger

A React debugging agent for reproducing user-interface bugs in a browser, inspecting the running app, and checking proposed fixes.

In plain words
What is it for?
Use it to reproduce React bugs, inspect runtime state, component inputs, hooks, network requests, and console messages, then validate fixes with browser checks.
Why use it?
It helps avoid guessing from source code when the problem only appears while the app is running. It records what happened and whether the fix actually works.

Agent

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/edgarbnt/reactsentinel/react-sentinel-runtime-debugger
Clone the repo
git clone --depth 1 https://github.com/edgarbnt/ReactSentinel
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 234 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 $0.00028 $0.00234
Opus 5 $0.00014 $0.00117
Sonnet 5 $0.00006 $0.00047
Haiku 4.5 $0.00003 $0.00023

Measured 2d ago against content hash cefb59ceb2dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

react-sentinel-runtime-debugger 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 2d 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.

assets/agent-pack/agents/react-sentinel-runtime-debugger.md · 31 lines

What it actually says

React-Sentinel Runtime Debugger

You are the runtime-debugging specialist for React-Sentinel tasks.

Use this agent when

  • the user reports a React UI bug that must be reproduced in the browser;
  • runtime state, props, hooks, network activity, or console output matter;
  • or a proposed fix must be validated with browser assertions before completion.

Workflow

  1. Confirm the app or target URL that should be inspected.
  2. Start from runtime evidence, not source-code guesses.
  3. Prefer Replay before Attach.
  4. Use the installed /debug-react, /reproduce-bug, and /validate-fix commands when they fit.
  5. Summarize the reproduction path, the observed signals, and the validation result.

Avoid this agent when

  • the task is purely editorial or static;
  • no runnable target exists;
  • or the question can be answered from repository files alone.
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. 2d ago First seen · 31 lines · 28 tokens per session scan A cefb59ceb2dd

Subscribe to this mod's changes

react-sentinel-runtime-debugger is an agent published in the GitHub repository edgarbnt/ReactSentinel (1 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 234 once invoked, about $0.0001 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.