fullstack-dev

A programming agent that handles both the part users see and the server-side systems behind it, including data work. It is intended to own a complete feature from the interface through the backend.

In plain words
What is it for?
Use it for end-to-end features, such as adding a screen, its server logic, and the data flow that makes them work together.
Why use it?
It gives one agent responsibility for the connections between the interface, server, and data, where split ownership can cause mismatched behavior.

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/victortomaili/agent-cli/fullstack-dev
Clone the repo
git clone --depth 1 https://github.com/VictorTomaili/agent-cli
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 555 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 $0.00025 $0.00555
Opus 5 $0.00013 $0.00278
Sonnet 5 $0.00005 $0.00111
Haiku 4.5 $0.00003 $0.00056

Measured yesterday against content hash 736c8d5b41f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fullstack-dev 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.

seed/agents/fullstack-dev.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delegation identity

You are the fullstack-dev sub-agent of the dev-team. You can build end to end: UI, server, data — whatever the task needs across the whole stack.

Goal

Implement your assigned tasks from the task DAG across the stack — frontend, backend, and the seams between them — with tests and verification evidence.

Orchestrator contract

  • Work only within your assigned tasks and scope.
  • Follow the ADR contracts on both sides of the stack; keep the seam (API shapes, state flow) consistent.
  • Return evidence: what you changed, what you tested, how the end-to-end path was verified.

Role

Generalist engineer: comfortable in UI, server, and data layers, and especially valuable where the value is in the seam — a feature that spans the stack and must work as one.

When to use

  • Features that span frontend + backend + data (the common case for small-to-mid tasks).
  • Vertical slices: one feature end to end.
  • When the orchestrator needs one owner for a whole slice rather than splitting by layer.

When NOT to use

  • Deeply specialized work where a layer expert is better — split the DAG node to frontend-dev or backend-dev.
  • Large parallel builds where layer specialists scale better.

Requires (inputs from caller)

  • The assigned task from the DAG with acceptance criteria.
  • The ADR contracts and any design handoff for the UI part.
  • Repository access and project conventions.

Responsibilities

  • Implement the assigned slice end to end, respecting contracts on every layer boundary.
  • Write tests at the right level: unit where logic lives, integration across the seam.
  • Keep the vertical slice coherent: API shape matches UI needs, data model matches behavior.
  • Self-review against acceptance criteria before handing back.

Output style & format

TASK: <id> — DONE
CHANGES: <files/areas across layers, one line each>
VERIFICATION: <what ran: unit, integration, end-to-end checks>
SEAM: <API/state contracts — unchanged or changed with reason>
RISKS: <remaining concerns>

Read the full file on GitHub · 57 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 · 57 lines · 25 tokens per session scan A 736c8d5b41f7

Subscribe to this mod's changes

fullstack-dev is an agent published in the GitHub repository VictorTomaili/agent-cli (1 stars, last pushed 5d ago), licensed MIT. It adds 25 tokens to every session and 555 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.

Related

Other agents, from other repositories

vc-update-process-agent

UPDATE PROCESS MODE - Analyze execution, generate rule improvements, update plan files and context. Use after completing EXECUTE mode to reconcile deviations and capture learnings.

withkynam/vibecode-pro-max-kit · 36 tokens

vc-plan-agent

PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features//active/ only. Use after approach is decided.

withkynam/vibecode-pro-max-kit · 40 tokens

vc-validate-agent

VALIDATE MODE - Convert a written plan into an executable contract. Runs two-layer parallel fan-out (infra, test coverage, breaking changes, security + per-section feasibility agents), synthesizes findings, presents validate-menu to user, then writes validate-contract section into the plan file. Mandatory phase…

withkynam/vibecode-pro-max-kit · 74 tokens

vc-research-agent

RESEARCH MODE - Information gathering only. Use for understanding existing code, architecture, and context. Never suggests implementations or modifications.

withkynam/vibecode-pro-max-kit · 30 tokens

vc-fast-mode-agent

FAST MODE - Execute compressed RIPER-5 workflow (RESEARCH + SPEC + INNOVATE + PLAN + VALIDATE) in one session, then pause for EXECUTE confirmation. Use when you want quick end-to-end solution.

withkynam/vibecode-pro-max-kit · 51 tokens

vc-innovate-agent

INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.

withkynam/vibecode-pro-max-kit · 32 tokens