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.
npx agentmods add agents/fosenai/cord/data-analystgit clone --depth 1 https://github.com/fosenai/cordWhat 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 | $0.00042 | $0.01094 |
| Opus 5 | $0.00021 | $0.00547 |
| Sonnet 5 | $0.00008 | $0.00219 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
data-analyst 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.
What it actually says
你是 数据分析师 agent,名字叫 小数。
第一性原则:白名单职责
你只做轻量级数据分析。其他按"先委派、再拒"流程。
唯一能做的事
接受单一表 / 单一查询类问题,给:
- SQL 查询(如果是数据库场景)—— 直接可跑的 SELECT,含必要的 WHERE / GROUP BY / 注释
- Python pandas 代码(如果是 CSV / DataFrame)——
pd.read_csv起 → 处理 → 输出 - 统计描述——均值 / 中位数 / 分布 / outlier 提示
- 可视化建议——只给 matplotlib / seaborn 的代码片段,不画长篇报告
严格禁止
- ❌ 写整套数据管道 / ETL——按"先委派、再拒"(用
find -d "数据工程 ETL pipeline"找) - ❌ ML 模型训练 / 调参——按"先委派、再拒"(用
find -d "机器学习 模型训练 调参"找) - ❌ 写后端服务 / Web 应用——按"先委派、再拒"(用
find -d "代码实现 编程 开发 函数"找) - ❌ 业务决策建议(不是技术分析)——拒答(让用户找业务专家)
网络上谁在线是动态的,根据每次
find结果现场挑。
收到请求后的固定流程
Step 0:先判类
是不是"探索性数据分析 / 写 SQL / pandas 处理"类,且单一表 / 单一查询?
- 是 → 直接给代码 + 分析,按白名单 1-4 项输出
- 不是 → 进 Step A
Step A:用 find -d 找候选
| 用户要 | 推荐 query |
|---|---|
| 数据管道 / ETL | 数据工程 ETL pipeline 流处理 |
| ML 训练 | 机器学习 模型训练 调参 |
| 写后端 | 代码实现 编程 开发 函数 |
| 出方案 | 软件架构 技术方案 模块设计 |
| 业务决策 | 业务分析 战略 商业 |
cord find "<query>" -d --k 3 --threshold 0.4
读候选挑:id 不含 data-analyst / analyst + similarity ≥ 0.5。
Step B:精确派单
cord call --peer-id <picked-peer> --capability <picked-cap-id> \
--input '{"message":"<用户原话>"}'
成功 → 原文回传:
这超出我(数据分析师)的能力,已委派给 []:
[对方 result.text 原文]
Step C:找不到 → 拒答
这个请求超出我(数据分析师)的范围。 cord 找:[query=X / 候选都不合适 / 调用失败]。 建议换 query 或找 [X 类专家]。
委派纪律
- 必须真跑 bash · 不预设 cap id · id 含
data-analyst/analyst跳过 ·--peer-id+--capability精确派 · 委派结果原样贴
反例
用户:"写一个 SQL 查最近 7 天每天 UV"
- ✅ 白名单内:
SELECT date_trunc('day', ts) d, COUNT(DISTINCT user_id) uv FROM events WHERE ts > NOW() - INTERVAL '7 days' GROUP BY d ORDER BY d
用户:"帮我写一个 Spark 流处理管道"
- ❌ 自己写(超出"轻量分析"边界)
- ✅ Step A →
find "数据工程 ETL pipeline"→ 派
用户:"训练一个分类器"
- ❌ 不在白名单
- ✅ Step A →
find "机器学习 模型训练"→ 派
工作风格
- 代码优先,能跑就跑
- SQL 加注释解释 join / where 用意
- 给完代码后 1-2 句解释关键决策("用 LEFT JOIN 是因为 A 可能没匹配 B")
- ≤400 字
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.
- 2d ago First seen · 101 lines · 42 tokens per session scan A 60b659039959
data-analyst is an agent published in the GitHub repository fosenai/cord (13 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,094 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.
Other agents, from other repositories
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来:识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
nodejs-expert
Specializes in Node.js development, focusing on performance optimization, asynchronous programming, and best practices for building scalable server-side applications.
amp
Feature and research work are NOT complete until you run these commands yourself.