What is server-agent?

A set of instructions for maintaining server code, including HTTP handlers, routes, middleware, API composition, and internal communication endpoints.

Use it when changing backend-for-frontend handlers, gateways, internal RPC endpoints, routes, middleware, authentication integration, or request and response adaptation.

It keeps request handling and protocol changes in the server layer while leaving business rules in service code.

How openclosed-org/axum-harness configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to openclosed-org/axum-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/openclosed-org/axum-harness/main/.agents/skills/server-agent/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/openclosed-org/axum-harness

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/openclosed-org/axum-harness/server-agent/github.svg)](https://agentmods.dev/skills/openclosed-org/axum-harness/server-agent)

Your own site

<a href="https://agentmods.dev/skills/openclosed-org/axum-harness/server-agent"><img src="https://agentmods.dev/badge/skills/openclosed-org/axum-harness/server-agent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/openclosed-org/axum-harness/server-agent"><img src="https://agentmods.dev/badge/skills/openclosed-org/axum-harness/server-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 680 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00081	$0.00680
Opus 5.5	$0.00032	$0.00272
Sonnet 5.5	$0.00016	$0.00136
Haiku 4.5	$0.00008	$0.00068

Measured 2mo ago against content hash 6bab192b7bfe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

server-agent 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 2mo 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/skills/server-agent/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Server Agent

You maintain server entrypoints — HTTP handlers, routes, middleware, and API composition.

Responsibility

Own servers/bff/web-bff/** — Web Backend-for-Frontend
Own servers/gateway/** — Edge gateway
Own servers/internal-rpc/** — Internal RPC server
Handle request/response adaptation, authn/z integration, API composition
Keep domain rules in services/**, not in servers

Read Before Editing

AGENTS.md                                → global protocol
agent/codemap.yml                        → module constraints (servers layer)
.agents/skills/backend-engineering/SKILL.md → backend quality kernel
services/<name>/model.yaml               → service commands / queries / consistency expectations
packages/contracts/**                    → shared protocol definitions

Writable Directories

Directory	Scope
`servers/bff/web-bff/**`	Web BFF handlers, routes, middleware
`servers/gateway/**`	Gateway configuration, routes
`servers/internal-rpc/**`	Internal RPC definitions
`packages/contracts/**`	When protocol changes are needed

Forbidden Directories

Directory	Reason
`services//domain/*`	Core domain logic owned by service-agent
`infra/**`	Owned by platform-ops-agent
`workers/**`	Owned by worker-agent
`packages//adapters/`	Concrete adapter implementations

Gate Candidates

Select gates from agent/manifests/gate-matrix.yml based on changed paths, risk, and evidence level. Common server signals include:

Gate	Command
Server build check	`cargo check -p <server-package>`
Typecheck	`just typecheck`
Boundary check	`just boundary-check`

Hard Rules

Workflow skills, including backend-engineering, may guide process; this skill's ownership boundaries still apply.

Servers may import services/** and packages/**
Server handlers must align with packages/contracts/**
Protocol changes: update contracts first, then handlers
Servers must NOT implement domain logic
Servers must NOT implement long transactions — those belong in workflow models
Servers must respect service-declared consistency expectations when exposing query endpoints
Servers must NOT import infra/**

Read the full file on GitHub · 94 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.

2mo ago First seen · 94 lines · 81 tokens per session scan A 6bab192b7bfe

Subscribe to this mod's changes

server-agent is a skill published in the GitHub repository openclosed-org/axum-harness (51 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 680 once invoked, about $0.0003 per session on Opus 5.5. 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.

Backend and APIs ai-agents axum-framework distributed-systems microservices platform-engineering

server-agent next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
server-agentopenclosed-org/axum-harness	Skill	51	5mo ago	Apache-2.0	A	81	Claude Code, Codex
architecture-paradigm-microservicesathola/claude-night-market	Skill	348	yesterday	MIT	A	33	Claude Code
microservices-expertpersonamanagmentlayer/pcl	Skill	44	11d ago	Apache-2.0	A	52	Claude Code
microservices-patternsbooklib-ai/booklib	Skill	40	7mo ago	MIT	A	131	Claude Code, Codex
distributed-feasibility-checkerbookforge-ai/bookforge-skills	Skill	42	6mo ago	CC-BY-SA-4.0	A	86	Claude Code
api-testing-patternsproffesor-for-testing/agentic-qe	Skill	525	yesterday	MIT	A	34	Claude Code
contract-testingproffesor-for-testing/agentic-qe	Skill	525	yesterday	MIT	A	35	Claude Code

axum-harness: Skill for Claude Code