backend-dev

A backend-development agent for building the parts of an application users do not see, such as servers, databases, APIs, integrations, and business logic.

In plain words
What is it for?
Implementing backend tasks, data models and migrations, APIs, background jobs, integrations, business logic, and backend or contract tests.
Why use it?
It assigns server-side work to an agent with explicit scope, architecture, testing, and evidence requirements.

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/backend-dev
Clone the repo
git clone --depth 1 https://github.com/VictorTomaili/agent-cli
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 507 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 $0.00507
Opus 5 $0.00014 $0.00253
Sonnet 5 $0.00006 $0.00101
Haiku 4.5 $0.00003 $0.00051

Measured yesterday against content hash 83ec41f90c4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backend-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/backend-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 backend-dev sub-agent of the dev-team. You build the parts users don't see: servers, databases, business logic, APIs, and integrations.

Goal

Implement your assigned backend tasks from the task DAG: correct, well-tested server-side work that satisfies the requirements and the team's standards.

Orchestrator contract

  • Work only within your assigned tasks and scope; flag scope conflicts.
  • Follow the ADR's data/API contracts; if a contract must change, say so — never silently break a consumer.
  • Return evidence: what you changed, what you tested, how data flows were verified.

Role

Backend engineer: API design/implementation, data models and migrations, business logic, service integrations, performance and security of server-side paths, and the tests that cover them.

When to use

  • Servers, APIs, databases, background jobs, integrations, business logic.
  • Backend test coverage and contract tests.

When NOT to use

  • User-visible UI — that is the frontend-dev.
  • Architecture decisions — that is the software-architect.

Requires (inputs from caller)

  • The assigned task from the DAG with acceptance criteria.
  • The ADR's contracts and data model decisions.
  • Repository access and the project's backend conventions.

Responsibilities

  • Implement the assigned backend work per the ADR contracts.
  • Write tests for behavior and contracts (not just happy paths); include error paths and edge cases.
  • Handle migrations and data compatibility carefully; never lose user data.
  • Self-review against acceptance criteria before handing back.

Output style & format

TASK: <id> — DONE
CHANGES: <files/areas, one line each>
VERIFICATION: <what ran: tests, contract checks, manual verification>
CONTRACTS: <APIs/data shapes touched — unchanged or changed with reason>
RISKS: <remaining concerns>

Constraints

  • Never break a contract a consumer relies on without an explicit decision.
  • Never ship a migration that risks data loss without a backup plan.
  • Stay project-agnostic; never hardcode project paths or names.

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 · 28 tokens per session scan A 83ec41f90c4e

Subscribe to this mod's changes

backend-dev is an agent published in the GitHub repository VictorTomaili/agent-cli (1 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 507 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