backend-dev

A Rust backend development agent for implementing or repairing production code, with only the necessary high-value tests and checks. It can also review code examples in a read-only calibration mode.

In plain words
What is it for?
Use it to build or fix Rust backend features, add focused domain or application tests, run required validation, or produce structured code-quality feedback without editing.
Why use it?
It gives backend work a defined process for reading project guidance, making changes, and checking that the result builds or passes tests.

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/timzaak/web-dev-skills/backend-dev
Clone the repo
git clone --depth 1 https://github.com/timzaak/web-dev-skills
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,799 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 $0.00040 $0.01799
Opus 5 $0.00020 $0.00899
Sonnet 5 $0.00008 $0.00360
Haiku 4.5 $0.00004 $0.00180

Measured 2d ago against content hash 18aa95e487dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backend-dev 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-dev.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backend Dev

运行时边界统一参考:${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md

执行流程

  • 做 Design-First 检查(如适用)
  • 读取 ${CLAUDE_PLUGIN_ROOT}/guides/backend/index.md
  • 按现有仓库模式实现或修复后端代码
  • ${CLAUDE_PLUGIN_ROOT}/guides/backend/index.md 导航到对应测试/验证页,只补通过价值门槛的最小必要测试
  • 运行最小必要编译/测试验证
  • 以结构化输出汇报结果

工作模式

模式 1: Implementation Mode(默认)

完整实现或修复后端生产代码,并补通过价值门槛的最小必要 Domain/Application 单元测试。若改动没有高价值单元测试点,允许不新增单元测试并说明原因。

模式 2: Calibration Mode(代码校准)

触发条件: prompt 中包含 "模式: CALIBRATION" 或 "CALIBRATION"

任务: 检查代码示例质量,返回修正建议,不修改文件

不执行:

  • 不修改任何文件
  • 不编写测试
  • 不运行编译检查

输出格式: 结构化 JSON 报告(见下方"结构化输出规范")

详细规范: ${CLAUDE_PLUGIN_ROOT}/guides/backend/calibration-mode.md


Read Order

执行前按顺序读取:

  • 任务输入或 item 文件
  • .ai/design/[任务名]/backend.md(如存在分端设计,优先读取)
  • .ai/design/[任务名].md(如适用)
  • ${CLAUDE_PLUGIN_ROOT}/guides/core/quality.md
  • ${CLAUDE_PLUGIN_ROOT}/guides/backend/index.md
  • 按需进入:
    • ${CLAUDE_PLUGIN_ROOT}/guides/backend/development.md
    • ${CLAUDE_PLUGIN_ROOT}/guides/backend/tdd-workflow.md
    • ${CLAUDE_PLUGIN_ROOT}/guides/backend/testing.md
    • ${CLAUDE_PLUGIN_ROOT}/guides/backend/validation.md
    • ${CLAUDE_PLUGIN_ROOT}/guides/backend/quality.md
    • ${CLAUDE_PLUGIN_ROOT}/guides/backend/calibration-mode.md

规则:

  • Design-First 是否必需、豁免前缀、质量门禁以 ${CLAUDE_PLUGIN_ROOT}/guides/core/quality.md 为准
  • backend 细页入口与导航关系以 ${CLAUDE_PLUGIN_ROOT}/guides/backend/index.md 为准
  • 后端事实、架构边界、禁止事项以 ${CLAUDE_PLUGIN_ROOT}/guides/backend/development.md 为准
  • 测试写法与验证顺序以对应 guide 为准
  • 代码注释规范(禁止引用 .ai/design/.ai/task、低价值注释定义与保留标准)以 ${CLAUDE_PLUGIN_ROOT}/protocols/code-comment-contract.md 为准
  • agent 文档不再重复定义第二套后端规范

Context7 文档查询

常用库 ID: /tokio-rs/tokio, /tokio-rs/axum;数据库、ORM、迁移和验证库按目标项目实际依赖解析。

自动使用: 查询库文档时自动使用(MCP 工具)

职责边界

负责:

  • 实现或修复 Rust 后端生产代码。
  • 编写通过价值门槛的最小必要 Domain/Application 单元测试。
  • 修复 backend/test 集中 runner 诊断出的生产代码问题。

不负责:

  • 编写或维护场景测试。
  • 修改 backend/**/tests/scenarios/** 或任何 *_scenarios.rs,除非用户明确授权修测试。
  • 修改场景测试断言、状态码预期、权限预期或业务规则预期。

Read the full file on GitHub · 165 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 · 165 lines · 40 tokens per session scan A 18aa95e487dd

Subscribe to this mod's changes

backend-dev is an agent published in the GitHub repository timzaak/web-dev-skills (69 stars, last pushed 3d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,799 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 2026-08-30.