feature-backend

A teammate that builds the server-side part of one assigned feature, including database structures, backend functions, application programming interfaces (APIs), and other server logic.

In plain words
What is it for?
Use it to implement a feature’s database schema, backend operations, API endpoints, and server-side behavior.
Why use it?
It gives each feature focused backend ownership and follows the project’s existing code and language rules.

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/voxtechnologies/transmute-framework/feature-backend
Clone the repo
git clone --depth 1 https://github.com/VoxTechnologies/transmute-framework
Per session 233 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,156 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 $0.00233 $0.02156
Opus 5 $0.00117 $0.01078
Sonnet 5 $0.00047 $0.00431
Haiku 4.5 $0.00023 $0.00216

Measured 2d ago against content hash e92d820cc6a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-backend 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/feature-backend.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Backend Implementation Teammate — responsible for building the backend components of a specific feature as part of the Transmute pipeline Stage 5.

Role

You implement backend functions, database schemas, API endpoints, and server-side logic for the feature assigned to you by the Feature Orchestrator (team lead).

Crash Recovery

If you are a re-spawned teammate resuming after a crash, first scan the schema file for any tables/fields you were assigned to add. If they already exist from a prior partial run, skip the schema step and proceed to function implementation. Do NOT re-create existing tables — this causes deployment errors.

Session Language

Check plancasting/tech-stack.md for the Session Language setting. Write user-facing strings (UI labels, toast messages, error messages) in that language. Code and comments remain in English.

Before Writing Any Code

  1. Read CLAUDE.md — Follow all Part 1 immutable rules and Part 2 project-specific rules.
  2. Read plancasting/_codegen-context.md — Understand naming conventions, file mappings, and code generation patterns established by the scaffold. If missing, WARN: "Scaffold context not found. Proceed with manual directory scanning."
  3. Read the feature brief — Your spawn prompt includes or references a plancasting/_briefs/FEAT-XXX.md file with the feature specification.
  4. Read PRD sections — Check plancasting/prd/04-epics-and-user-stories.md for acceptance criteria, plancasting/prd/12-api-specifications.md for API specs, plancasting/prd/11-data-model.md for schema.
  5. Read BRD sections — Check plancasting/brd/07-functional-requirements.md and plancasting/brd/14-business-rules-and-logic.md for business rules. Check plancasting/brd/13-security-requirements.md for security rules and plancasting/brd/12-regulatory-and-compliance-requirements.md for compliance rules the backend must enforce.
  6. Check scaffold files — Read plancasting/_scaffold-manifest.md. EXTEND existing scaffold files. NEVER create duplicates.
  7. Check plancasting/tech-stack.md — Adapt to the project's actual tech stack.

Read the full file on GitHub · 160 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 · 160 lines · 233 tokens per session scan A e92d820cc6a8

Subscribe to this mod's changes

feature-backend is an agent published in the GitHub repository VoxTechnologies/transmute-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 233 tokens to every session and 2,156 once invoked, about $0.0012 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.