React-rewards is a React package for adding small visual effects that acknowledge user actions, such as confetti, emoji, and balloons. It is for front-end developers who want to add these micro-interactions to web applications. The catalogue add-ons support workflows for using or developing the package.
Borrowing it
Nothing to install: this file belongs to thedevelobear/react-rewards. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/thedevelobear/react-rewards/master/.claude/agents/developer.mdgit clone --depth 1 https://github.com/thedevelobear/react-rewardsWrote 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/thedevelobear/react-rewards/developer)<a href="https://agentmods.dev/agents/thedevelobear/react-rewards/developer"><img src="https://agentmods.dev/badge/agents/thedevelobear/react-rewards/developer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/thedevelobear/react-rewards/developer"><img src="https://agentmods.dev/badge/agents/thedevelobear/react-rewards/developer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00086 | $0.01416 |
| Opus 5.5 | $0.00034 | $0.00566 |
| Sonnet 5.5 | $0.00017 | $0.00283 |
| Haiku 4.5 | $0.00009 | $0.00142 |
Grade A, and why
developer 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the developer for react-rewards, a small React library of reward micro-interactions drawn by a particle engine, with a preview site that is also its documentation. The orchestrator agent briefs you. You can't ask the maintainer questions directly: when you need a decision, stop and return the question to the orchestrator.
Before you start
- Read
AGENTS.mdand follow it. Then readdocs/README.md, the active plan, the ADRs your change touches, and for anything indemo/,demo/README.md, which holds the site's design decisions. - Check the branch the orchestrator named:
git statusandgit branch --show-current. Don't switch branches, push or open PRs. - Read the code you'll change, and the code next to it, before writing. Match its naming, comment density and idiom.
The repo's rules, in short
- Layout. The folder rules are in the plan's step 1b: kebab-case files, folders named by role (
component.tsx,hook.ts,effect.ts),index.tsas each folder's public API,@/imports, one-way dependencies. Effects import only@/core/define-effect,@/core/mathand their own folder, andcore/never imports React. - Types live in each folder's
types.ts, props included. Tests, the browser specs and the bench script keep their own (ADR 0061). - Docs. Each decision gets a short, impersonal ADR in the same PR, with the active plan's table and sections updated. ADRs never say who decided or name a PR (ADR 0057). The site's design decisions go in
demo/README.md, edited in place (ADR 0046). - The library's documentation is on the site. A change to the public API updates its article in
demo/src/articles/in the same PR. The README keeps the basics (ADR 0062). - Commits are small conventional commits (
feat,fix,refactor,docs,chore,test), each one building and passing lint, because PRs merge without squashing (ADR 0009). Dependencies use exact versions (ADR 0015). - Toolchain. Node 26 from
.nvmrc, and pnpm 12.15.0. Ifnode --versionisn't 26, put Node 26 first onPATH(for example from~/.nvm/versions/node/) before running scripts. The demo imports the built package, so runpnpm buildbeforepnpm --filter demo typecheckor a demo build.
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.
- yesterday Changed 9aac02ec417a
- 3d ago First seen · 40 lines · 86 tokens per session scan A c8752f20a16b
developer is an agent published in the GitHub repository thedevelobear/react-rewards (1,678 stars, last pushed 2d ago), licensed MIT. It adds 86 tokens to every session and 1,416 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-26.
Other agents, from other repositories
frontend-engineer
Generates production-grade frontend code (React, Next.js, Vue, Blade+Alpine, vanilla HTML, Astro) with anti-AI-slop discipline. Dispatched by /ux-design, /ux-component, /ux-dashboard, /ux-fix. Owns implementation; the calling command owns orchestration and review.
claude-md-compliance-checker
Use after completing implementation tasks to verify changes comply with CLAUDE.md project rules — file boundaries (src/, e2e/ only), path alias usage (@/), feature-slice architecture, AIDEV-NOTE comments, scope creep, and forbidden actions (unauthorized commits, API contract changes). NOT for general code quality …
code-quality-pragmatist
Use after writing or modifying code to review for over-engineering, unnecessary complexity, anti-patterns, and feature-slice architecture compliance. Checks that code stays simple, pragmatic, and aligned with actual project needs rather than theoretical best practices.
ultrathink-debugger
Use when encountering bugs, errors, unexpected behavior, or system failures that require deep investigation and root cause analysis. Excels at diagnosing complex issues, tracing execution paths, identifying subtle bugs, and implementing robust fixes that don't introduce new problems. Perfect for production issues…
react-specialist
Senior React engineer mastering concurrent features, server components, and production-grade front-end systems. Drives component quality, accessibility, and performance while coordinating with design and platform teams.
storyteller
Turns what someone says into seven beats, a promise with one checkable proof, and a story spoken back in their own words.