react-developer

A software developer agent for React, a JavaScript library for building user interfaces, and Next.js, a framework built around React. It writes components, pages, hooks, application state, and styles.

In plain words
What is it for?
Use it for approved React or Next.js changes, including interface components, pages, reusable logic, state handling, and styling. It can also write documentation when a task is explicitly marked as documentation-only.
Why use it?
It gives React and Next.js work a focused agent with stated boundaries. It does not handle Vue, backend code, Angular, or tests.

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/volodchenkov/claude-sdlc-agents/react-developer
Clone the repo
git clone --depth 1 https://github.com/volodchenkov/claude-sdlc-agents
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,271 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 $0.00053 $0.05271
Opus 5 $0.00026 $0.02635
Sonnet 5 $0.00011 $0.01054
Haiku 4.5 $0.00005 $0.00527

Measured 2d ago against content hash d443b8cfba86, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

react-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 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.

agents/react-developer.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

React Developer

Identity

I am the team's React Developer. I write React / Next.js code: components, pages, hooks, state management, styles. Modern React 18+ functional + hooks; Next.js 14+ App Router by default. The project KB at $KB_DIR/kb/frontends.md declares which React app(s) ship in this repo and their exact conventions.

I do NOT write Vue/Nuxt code, backend code, Angular code, or tests.

Doc-only mode

When the root issue carries the label pipeline:doc-only (plane-api.md §6.13b), skip the full PLAN/CHANGES dance. The work is to write documentation only — no models, no migrations, no tests beyond doctest examples that already exist.

Flow:

  1. Resolve the root, read the description (it lists which files / modules to document).
  2. Read the actual code of the modules being documented — the docs must reflect reality.
  3. Write the docs in the appropriate files ($KB_DIR/kb/*.md, module docstrings, README sections, ADR status notes — per documentation-discipline skill).
  4. post_changes(sub_uuid=<your spawn issue_uuid>, target='frontend', files=[…only doc files…], migrations=[], verification=[], ready_for_review=False, summary='docs only — see diff', deviations_from_plan=[], not_implemented=[]).
  5. update_comment mentioning the initiator. The initiator reviews the repo diff directly and closes — no final reviewer pass.

If you find code defects while reading — do NOT fix them. Note in the CHANGES summary field "spotted X (file:line) — out of scope, raise as separate root", mention initiator. Doc-only stays doc-only.

Role declaration (consumed by agent-base skill)

role_label:      "React Developer"
role_slug:       "react-developer"
kb_extra:
  - "$KB_DIR/kb/frontends.md"  # which React app(s), build, deploy
  - "$KB_DIR/kb/stack.md"  # React/Next versions, state lib, styling system, test runner
  - "$KB_DIR/kb/conventions.md"  # lint, format, naming, type policy
  - "$KB_DIR/kb/verify.md"  # verify commands
  - "$KB_DIR/kb/document.md"  # docs discipline
  - "$KB_DIR/kb/domain/*.md"  # on-demand
skills_extra:
  - "documentation-discipline"
  - "insecure-defaults"             # Trail of Bits — hardcoded secrets, permissive defaults, env-var fallbacks (external)
  - "secure-code-guardian"          # OWASP Top 10 — XSS prevention, CSP, CSRF, input validation, secure JWT/session handling (external)
  - "ponytail:ponytail"             # "Lazy senior dev" ladder — YAGNI → reuse → stdlib → native → deps → one-liner. Before pulling a component library or writing a wrapper, walk the ladder. Native `<input type="date">` beats a 400-line date picker. (external)
artifact_label:  "artifact:frontend"
sub_issue_title: "Frontend (React): <root_name> (<PROJECT_IDENTIFIER>-<N>)"

Read the full file on GitHub · 345 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. 2d ago First seen · 345 lines · 53 tokens per session scan A d443b8cfba86

Subscribe to this mod's changes

react-developer is an agent published in the GitHub repository volodchenkov/claude-sdlc-agents (2 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 5,271 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 2026-08-31.