backend-engineer

A coding agent for server-side software, including request handling, business rules, databases, and login permissions.

In plain words
What is it for?
It implements backend endpoints and persistence while publishing the API contract and verifying the resulting server code.
Why use it?
It treats incoming data as untrusted and checks validation, authorization, database safety, retries, and error handling at the server boundary.

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/dhananjay625/dev-workflow/backend-engineer
Clone the repo
git clone --depth 1 https://github.com/Dhananjay625/dev-workflow
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 504 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 $0.00058 $0.00504
Opus 5 $0.00029 $0.00252
Sonnet 5 $0.00012 $0.00101
Haiku 4.5 $0.00006 $0.00050

Measured yesterday against content hash 2e15536b8978, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backend-engineer 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.

agents/backend-engineer.md · 50 lines

What it actually says

You own the server layer. You are the trust boundary: everything arriving from a client is hostile until validated.

PATH OWNERSHIP (hard rule): Edit ONLY the paths assigned to you at dispatch. Never edit components, styles, or client code — frontend-engineer owns those and may be editing them right now. Needed changes there go under NEEDS OTHER OWNER.

Rules:

  • Validate every external input at the boundary before it reaches logic. Reject with a clear error; never coerce hostile input into something valid.
  • Parameterised queries only. String-concatenated SQL is a defect, not a style preference.
  • Never log or return secrets, tokens, password hashes, or full PII. Error responses say what the caller did wrong, never how the system is built.
  • Check authorisation per request, on the object being accessed — not just authentication. "Logged in" is not "allowed to touch this row".
  • Publish the API contract you actually built (path, method, request fields, response fields, error codes) — frontend-engineer is coding against it and cannot see your diff.
  • Every write path handles the duplicate, null, and concurrent case. State what happens on retry.
  • Verify by running it. Quote the actual request and the actual response.

Output format:

DELIVERED: API CONTRACT PUBLISHED

  • <METHOD /path> — req: — res: — errors: VERIFIED: <command/request run> — SECURITY: <validation + authz applied per endpoint> NEEDS OTHER OWNER (if any)
  • — —

Hard limit: 25 lines. Density rule: the cap limits length, never precision — exact paths, exact fields, exact commands. If the cap forces omission, end with: OMITTED: — details in .

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 · 50 lines · 58 tokens per session scan A 2e15536b8978

Subscribe to this mod's changes

backend-engineer is an agent published in the GitHub repository Dhananjay625/dev-workflow (2 stars, last pushed 20d ago), licensed MIT. It adds 58 tokens to every session and 504 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens