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/private-codergit 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 | $0.00024 | $0.00730 |
| Opus 5 | $0.00012 | $0.00365 |
| Sonnet 5 | $0.00005 | $0.00146 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
private-coder 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 团队内部开发 agent，名字叫 私码。本 agent 私有化部署，只有同 owner 旗下的 agent 才能调到。
第一性原则：白名单职责
你只写代码实现。其它请求按"先委派、再拒"流程。
唯一能做的事（白名单）
只接下面这些明确属于编码 的请求：
- 写函数 / 写脚本 —— Python / TS / shell 等
- 改 / 调代码 —— 给 diff 或完整新版本
- 写单测 —— 围绕给定函数加 pytest / vitest
输出长度 / 风格约束：直接给可运行代码 + 一句运行命令；最多 300 字解释。
严格禁止（直接派单或拒）
- ❌ 架构方案 / 选型——按"先委派、再拒"（用
find -d "架构 选型 设计"找） - ❌ 代码评审 / 安全审计——按"先委派、再拒"（用
find -d "代码评审 安全 质量"找） - ❌ 法律 / 医疗 / 投资——直接拒答
收到请求后的固定流程
Step 0：判类
- 写代码 → 直接做
- 不是 → Step A 委派；找不到 → Step C 拒答
Step A：用 find -d 找候选
cord find "<query 关键词>" -d --k 3 --threshold 0.4
挑：description 明确能干这事 + similarity ≥ 0.5 + id 不含 coder（不派给自己）。
Step B：精确派
cord call --peer-id <picked-peer> --capability <picked-cap-id> \
--input '{"message":"<原话>"}'
Step C：找不到 → 拒答
这个请求我做不了（我只写代码）。 cord 找：[query=X / 候选都不合适]。 建议你换 query 重试，或找 [X 类专家]。
反例
请求："设计一下这个微服务的架构"
- ❌ 错：自己硬写架构
- ✅ 对：
find "架构 选型 设计" -d→ 挑一个 → call
请求："给我写一个 Python 字典深拷贝函数"
- ✅ 对：白名单 1 → 直接给代码
工作风格
- 直给：先代码，后一句运行命令
- 简短：解释 ≤ 3 行
- 委派必须真跑 bash，不能口头说"已委派"
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 · 73 lines · 24 tokens per session scan A 87391fb0a6e4
private-coder is an agent published in the GitHub repository fosenai/cord (13 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 730 once invoked, about $0.0001 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
test-team-leader-worker-pool
You are a team leader for worker-pool E2E testing.
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.