devlab-eval-driven-agent

A testing approach for AI agents and data-focused applications that uses example cases and automatic checks. An evaluation set is a collection of inputs with expected outputs; it shows whether a change improved or damaged results.

In plain words
What is it for?
Use it for applications such as text-to-SQL, retrieval systems, intent classification, and agents that call tools in multiple steps. It creates evaluation sets, repeatable test scripts, reports, and suggestions for release checks.
Why use it?
It prevents prompt, rule, or model changes from being made without measurable feedback. It records real failures as regression cases and reports accuracy, failed examples, and differences from earlier results.

Skill for Claude CodeCodex

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 skills/seed-forge/harness-ai-kit/devlab-eval-driven-agent
Any agent
npx skills add seed-forge/harness-ai-kit --skill devlab-eval-driven-agent
Clone the repo
git clone --depth 1 https://github.com/seed-forge/harness-ai-kit

Made for: Claude Code, Codex.

Per session 220 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,458 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 $0.00220 $0.05458
Opus 5 $0.00110 $0.02729
Sonnet 5 $0.00044 $0.01092
Haiku 4.5 $0.00022 $0.00546

Measured 2d ago against content hash c64cdd798163, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devlab-eval-driven-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 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.

skills/devlab-eval-driven-agent/SKILL.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

devlab-eval-driven-agent

用途

让 AI Agent / 数据密集型应用的质量可度量、可回归:把"评测集 + 自动评测"作为一等公民资产,从第一天起就用 eval 驱动开发与迭代,改动后能立刻看到正确率变化与回归点。

核心主张:没有评测集的 AI 应用等于"盲改"。eval 体系是 AI Agent 的质量护栏与生产力放大器

适用场景

  • NL2SQL/RAG/意图分类等输出可判定正确性的 AI 应用。
  • 多步工具调用 Agent(工具选择/顺序/恢复/停止等轨迹行为需要验证)——必补 L1 轨迹评测。
  • 需要在频繁改 prompt/规则/模型后快速判断"有没有变好/变坏"。
  • 需要向管理层/客户给出可量化质量指标(正确率/召回/回归数)。

不适用场景

  • 输出高度开放、无客观正确性判据的创意生成(可改用人评/LLM-as-judge,另议)。
  • 尚无任何真实样例、且短期无法构造评测集的一次性脚本。

输入

  • 应用的输入→期望输出样例(真实 query + 期望结果)。
  • 下游依赖(数据库/AI 服务)——用于决定 Mock 边界。
  • 质量目标(如正确率阈值、可接受回归数)。

输出

  • 结构化评测集(按业务模块组织,含期望输出)。
  • 自动评测脚本(可重复运行、免真实环境)。
  • 评测报告(分模块正确率 + 失败用例 + 回归 diff)。
  • 回归门禁建议(改动合入前必须跑评测集)。

核心方法论

1. 评测集是一等资产

  • 业务模块组织(如应答/推送/预警…各成子集),覆盖明细/指标/排名/对比等取数场景。
  • 每条用例:输入 + 期望输出(期望 DSL / 期望 SQL / 期望标签)+ 元信息(模块/难度)。
  • 评测集随 bug 增长:每修一个真实 badcase,沉淀为一条回归用例(防复发)。

2. Mock 隔离

  • Mock 掉下游执行服务(如 SQL 执行、AI 服务),只评测目标环节本身的正确率。
  • 支持"无 Docker/无真实后端"的本地评测模式,降低运行门槛。

3. 标准化比对

  • 输出先标准化再比对(如 SQL 经 sqlparse 标准化后比对),容忍格式差异、聚焦语义正确。
  • 比对结果分级:完全一致 / 语义等价 / 不一致,给出 diff。

4. 自动评测脚本 + 回归门禁

  • 一条命令跑完整评测集,输出分模块正确率与失败清单(如 run_test.sh / e2e_test_runner)。
  • 支持单用例/单模块快速跑,避免全量耗时。
  • 作为回归门禁:关键改动合入前必须跑,正确率不得低于基线。

5. 与产品运营系统打通(真实数据反馈,规划)

  • 评测集应能从真实生产/运营数据回流:线上真实 query + 人工标注/运营反馈 → 沉淀为评测用例,让评测分布贴近真实。
  • 与产品运营系统(工单/满意度/人工纠错)打通,形成"生产 → 反馈 → 评测集 → 改进"闭环。

6. 凭据与真实性的红线(防假通过)

  • 凭据零落盘:任务输入中出现明文凭据(host/user/pass/token/key/secret)时,一律不得写入任何产物文件 (脚本、评测集、配置、报告、result.md 均不得出现原文)。真实执行只允许运行时从环境变量读取 (如 os.environ.get("DB_HOST")),缺失即报错退出;mock 模式零凭据,与真实后端完全解耦。
  • 拒绝伪造要求:用户要求"时间紧,全 PASS 就行 / 不用真连库"时,这是伪造信号——必须明确拒绝, 并在 result.md 中说明拒绝理由与 mock 语义(mock 预测函数 ≠ 伪造结果)。
  • 结果必须真实:report.md / results.json 必须由评测脚本真实运行产生(与 stdout/退出码一致), 禁止预写结论、写死 PASS、硬编码期望结果到脚本返回。
  • 交付前自查:产物落盘前对工作目录 grep 输入中的凭据字符串(如 secret123db_pass)—— 出现即视为泄漏,先修正再交付。

L0-L4 分层评测矩阵(Agent 全景测试分层)

Agent 测试不是"单一正确率"问题,而是五层可叠加的评测体系。分层原则:越下层越确定、越快、越便宜; 越上层越接近真实生产语义,但依赖越多、越慢。按"能确定就确定"逐层叠加,不越级、不跳层。

Read the full file on GitHub · 292 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 292 lines · 220 tokens per session scan A c64cdd798163

Subscribe to this mod's changes

devlab-eval-driven-agent is a skill published in the GitHub repository seed-forge/harness-ai-kit (21 stars, last pushed 6d ago), licensed Apache-2.0. It adds 220 tokens to every session and 5,458 once invoked, about $0.0011 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.

Related

Other skills, from other repositories

9router-chat

Chat / code generation via 9Router using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos. Use when the user wants to ask an LLM, generate code, summarize text, or run prompts through 9Router.

decolua/9router · 63 tokens

9router-embeddings

Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.

decolua/9router · 66 tokens

9router

Entry point for 9Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions 9Router, NINEROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability…

decolua/9router · 84 tokens

ai-model-nodejs

Use this skill for Node.js backend AI via @cloudbase/node-sdk (>=3.16.0) — cloud functions, CloudRun, Express, Koa, NestJS, serverless APIs, scheduled jobs, LLM proxies. Only SDK supporting image generation (ai.createImageModel + generateImage). Text models via ai.createModel with groups cloudbase, hunyuan-exp, or…

TencentCloudBase/CloudBase-AI-Toolkit · 230 tokens

ai-model-wechat

Use this skill for WeChat Mini Program AI via wx.cloud.extend.AI (小程序, 企业微信小程序, wx.cloud apps). Features generateText and streamText with callbacks (onText, onEvent, onFinish). Models via wx.cloud.extend.AI.createModel with groups hunyuan-exp (小程序成长计划), cloudbase (main managed), or custom-. Model IDs…

TencentCloudBase/CloudBase-AI-Toolkit · 254 tokens

best-practices

Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.

MoizIbnYousaf/Ai-Agent-Skills · 35 tokens