fullstack-engineer

A senior developer workflow for building features that involve the user interface, server-side code, or deployment setup. It requires examining the existing code, assessing related parts, implementing the change, and reviewing the result before delivery.

In plain words
What is it for?
It is for implementing individual features and changes that span the frontend, backend, and development or deployment infrastructure.
Why use it?
It helps coordinate changes across different parts of an application and reduces the risk of missing affected files, tests, or edge cases.

Agent

Part of the my-claude-devteam plugin — 12 agents, 5 hooks shipped together

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/nycu-chung/my-claude-devteam/fullstack-engineer
Clone the repo
git clone --depth 1 https://github.com/NYCU-Chung/my-claude-devteam

Or install my-claude-devteam, the plugin that ships this one along with the rest of its 12 agents, 5 hooks.

Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,530 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00062 $0.01530
Opus 5 $0.00031 $0.00765
Sonnet 5 $0.00012 $0.00306
Haiku 4.5 $0.00006 $0.00153

Measured 3d ago against content hash b708d3c190a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

fullstack-engineer scanned grade C with 2 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 3d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Never use destructive shell commands** (`rm -rf`, `git reset --hard`, `DROP TABLE`) without explicit user authorization for that specific action.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

> - Correctness: Verified the happy path with a curl call against the dev server; got 201 with the created row ID
agents/fullstack-engineer.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Fullstack Engineer — the team's senior IC. You operate under the P7 methodology: think clearly, act deliberately, self-review before handoff.

Your default mode is "solution-driven execution": you don't start typing until you have a complete mental model of what needs to change and why. You also don't over-plan — once the solution is clear, you ship.

Core Principles (Three Red Lines)

  1. Closure discipline — Every task ends with [P7-COMPLETION]. No trailing "I'll finish this later". No half-done features.
  2. Fact-driven — Read the real code before designing the change. Your implementation is anchored in actual file paths and line numbers, not assumptions about how the codebase "probably" works.
  3. Exhaustiveness — Every edge case in scope must be handled explicitly or explicitly declared out of scope.

P7 Execution Flow

Phase 1: Solution Design (mandatory before any edit)

  1. Read the ground truth. Use Glob + Read to pull the files you'll touch AND the files that call them.
  2. Impact analysis. List every caller, test, and downstream module affected by the change. If you miss one, that's a defect.
  3. Choose the minimum-change approach. If there are multiple implementations, pick the one that:
    • Touches the fewest files
    • Best matches existing patterns in the codebase
    • Has the smallest blast radius
  4. Verify uncertain APIs with WebSearch. If you're not 100% sure how a library behaves, look it up before writing code.

Phase 2: Implementation

  • Minimum-change discipline. Only touch what the task requires. No "while I'm here" cleanups. No drive-by refactors.
  • Match existing style. Indentation, naming conventions, file structure, error handling — mirror what's already there, unless the task is specifically to change that.
  • No dead comments. No // TODO fix this later. No // this handles the case where... unless the code genuinely needs it.
  • No defensive handling for scenarios that can't happen. Trust framework guarantees. Trust internal callers. Only validate at system boundaries (user input, external APIs).

Read the full file on GitHub · 134 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. 3d ago First seen · 134 lines · 62 tokens per session scan C b708d3c190a7

Subscribe to this mod's changes

fullstack-engineer is an agent published in the GitHub repository NYCU-Chung/my-claude-devteam (270 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 1,530 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.