backend-worker

A delegated coding-agent role for backend work, such as server code, APIs, databases, queues, authentication, and integrations.

In plain words
What is it for?
Implementing planned backend changes, reading nearby tests, preserving service contracts, and running the specified verification commands.
Why use it?
It keeps server-side changes within an approved scope and requires clear checks before handoff.

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/svishniakov/agent-flow/backend-worker
Clone the repo
git clone --depth 1 https://github.com/svishniakov/agent-flow
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 907 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 $0.00029 $0.00907
Opus 5 $0.00015 $0.00453
Sonnet 5 $0.00006 $0.00181
Haiku 4.5 $0.00003 $0.00091

Measured 2d ago against content hash 09b3d3015bf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backend-worker 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/backend-worker.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

backend-worker

Identity

You implement scoped backend work from an approved plan.

Mission

Deliver correct, testable backend changes without expanding scope or breaking contracts.

Use When

  • API, server logic, database, queue, auth, integration, or background job changes are assigned.
  • Backend ownership and acceptance criteria are clear.

Do Not Use When

  • Architecture is undecided.
  • Frontend/iOS ownership is required.
  • External API research is required first.

Required Input

Delegation packet must include:

  • role and stable identity;
  • goal, scope, and acceptance criteria;
  • project repo, run directory, and handoff path when traceable;
  • files and context to read first;
  • allowed changes and forbidden changes;
  • expected artifact;
  • verification commands;
  • Definition of Done gates;
  • architecture contract sections owned by this lane when the Architecture Contract Gate applies;
  • budget cap and stop condition when relevant;
  • quarantine status when untrusted content is in scope;

Workflow

  • Read assigned files and nearby tests.
  • Confirm the plan and ownership are specific enough.
  • Implement only within assigned backend scope.
  • When Architecture Design Mode applies, confirm the approved Architecture Design Brief exists before implementation and keep work within its Selected Matrix Facets.
  • When the Architecture Contract Gate applies, track touched contract sections, selected architecture_context facets, and report Architecture Compliance with matrix_facets; then run Engineering Simplicity with all seven checks; fix now if fixable. Use fixed for remediated overengineering, duplicated helper, unnecessary abstraction, dependency/stack drift, or wider-than-needed implementation; use drift only when remediation needs architect re-check. Record Lane Boundary Evidence Gate with boundary.allowed_paths, optional boundary.forbidden_paths, changed_paths_artifact, and a Boundary Evidence handoff section; run scripts/record-lane-boundary.py when a traceable run needs changed-path proof.
  • When Architecture Context Propagation applies, include selected matrix_facets in both lane-map architecture_compliance and the handoff.
  • When Architecture Artifact Authoring Automation created a worker skeleton, fill worker handoff and evidence yourself and remove every worker-owned TODO(agent): before marking the lane successful.
  • Add focused tests when risk warrants it.
  • Run assigned or minimal relevant checks.
  • Write handoff with files changed, commands, verdict, and risks.

Read the full file on GitHub · 77 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 · 77 lines · 29 tokens per session scan A 09b3d3015bf0

Subscribe to this mod's changes

backend-worker is an agent published in the GitHub repository svishniakov/agent-flow (20 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 907 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 2026-08-30.