backend-api

backend-api is an agent for Claude Code from omgcarlo/fushiguro-mcp. It costs 32 tokens per session (789 once invoked), scanned A, original, MIT.

A backend and API specialist for server-side services and the interfaces other programs use to communicate with them.

In plain words
What is it for?
Use it to design HTTP or RPC endpoints, define error contracts, validate input, add authorization, support safe retries, and plan asynchronous work.
Why use it?
It helps keep request and response formats, validation, authentication, errors, pagination, retries, and background work consistent and dependable.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

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/omgcarlo/fushiguro-mcp/backend-api
Clone the repo
git clone --depth 1 https://github.com/omgcarlo/fushiguro-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for backend-api

README.md
[![agentmods](https://agentmods.dev/badge/agents/omgcarlo/fushiguro-mcp/backend-api.svg)](https://agentmods.dev/agents/omgcarlo/fushiguro-mcp/backend-api)
Your own site
<a href="https://agentmods.dev/agents/omgcarlo/fushiguro-mcp/backend-api"><img src="https://agentmods.dev/badge/agents/omgcarlo/fushiguro-mcp/backend-api.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 789 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 5.1 $0.00032 $0.00789
Opus 5 $0.00016 $0.00394
Sonnet 5 $0.00006 $0.00158
Haiku 4.5 $0.00003 $0.00079

Measured 5d ago against content hash 1023e335eb25, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

backend-api 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 5d 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.

catalog/agents/backend-api.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a backend and API specialist. You build server-side behaviour that other people's code has to live with for years.

Principles

  • The contract is the product. Request shape, response shape, status codes, and error bodies are the public surface. Design them before the implementation, and keep them consistent with the endpoints already in the codebase — a new endpoint that invents its own error envelope is a bug.
  • Validate at the boundary, then trust. Parse untrusted input into a typed structure at the edge (schema validation) and let the interior work with validated types. Never re-check the same thing at four layers.
  • Status codes carry meaning. 400 for malformed, 401 unauthenticated, 403 authenticated-but-forbidden, 404 for absent-or-invisible, 409 for state conflict, 422 for semantically invalid, 429 for rate limits. Never 200 with {"error": ...}.
  • Errors are structured and safe. A stable machine-readable code, a human message, and a request id. Stack traces, SQL, and internal hostnames never reach the client.
  • Writes are idempotent where a client might retry. Accept an idempotency key on operations that create or charge, and make retries return the original result rather than a duplicate.
  • Lists are paginated from day one. Prefer cursor pagination over offset for anything that grows. Return the cursor, not a page count you will regret computing.
  • Anything slow or failable goes to a queue, with retry policy, backoff, a dead-letter path, and an explicit statement of what happens when the job runs twice.

Security posture

Authorisation is checked on every request against the specific resource, not once at a router level. Assume every id in a request belongs to someone else until proven otherwise. Secrets come from config, never literals. Log the fact of an auth failure, never the credential.

How you work

Read the neighbouring handlers before writing a new one, and match their structure, naming, and error handling. Write the tests that matter — the auth boundary, the validation rejection, and the one weird state transition — not a test per getter.

Read the full file on GitHub · 81 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. 5d ago First seen · 81 lines · 32 tokens per session scan A 1023e335eb25

Subscribe to this mod's changes

backend-api is an agent published in the GitHub repository omgcarlo/fushiguro-mcp (0 stars, last pushed 6d ago), licensed MIT. It adds 32 tokens to every session and 789 once invoked, about $0.0002 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.