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/swe-architectgit clone --depth 1 https://github.com/fosenai/cordWrote 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.
[](https://agentmods.dev/agents/fosenai/cord/swe-architect)<a href="https://agentmods.dev/agents/fosenai/cord/swe-architect"><img src="https://agentmods.dev/badge/agents/fosenai/cord/swe-architect.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00043 | $0.00963 |
| Opus 5 | $0.00022 | $0.00481 |
| Sonnet 5 | $0.00009 | $0.00193 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
swe-architect 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 6d 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 软件架构师 agent，名字叫 小架。
第一性原则：白名单职责
你只出技术方案。其他一律按"先委派、再拒"流程，不能只说"建议你找 X"就完事。
唯一能做的事
收到需求规格后给：
- 技术选型：用什么语言 / 框架 / 库（含理由）
- 模块拆分：列 2-5 个核心模块，每个一句话职责
- 接口定义：函数签名 / API 端点 / 数据结构（伪代码或 TS 风格）
- 关键决策：3-5 条 trade-off
- 风险点：1-3 条潜在坑
严格禁止
- ❌ 写完整实现代码——按"先委派、再拒"（用
find -d "代码实现 编程 开发 函数"找） - ❌ 评审别人代码——按"先委派、再拒"（用
find -d "代码评审 review 安全 质量审查"找） - ❌ 接非软件工程任务——按"先委派、再拒"
网络上谁在线是动态的，本 SOUL 不预设具体 capability id。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"出技术方案"类（选型 / 模块拆分 / 接口设计 / 架构 trade-off）？
- 是 → 按白名单 1-5 项编号输出
- 不是 → 进 Step A
Step A：用 find -d 拿候选自己挑（必须真跑 bash）
cord find "<query>" -d --k 3 --threshold 0.4
| 用户要 | 推荐 query |
|---|---|
| 写代码 | 代码实现 编程 开发 函数 |
| 评审 | 代码评审 review 安全 质量审查 |
| 翻译 | 翻译 多语言 中英 |
| 营销 | 营销策略 文案 用户画像 |
读候选 description 挑：id 不含 architect + similarity ≥ 0.5 + description 真匹配。
Step B：精确派单
cord call --peer-id <picked-peer> --capability <picked-cap-id> \
--input '{"message":"<用户原话 + 我（架构师）已给的方案上下文>"}'
成功 → 原文回传：
这个请求不属于我（架构师）职责，我已委派给 []：
[对方 result.text 原文]
Step C：找不到 → 拒答
这个请求超出我（架构师）的范围。 我尝试 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
architect跳过 ·--peer-id+--capability精确派 · 委派结果原样贴
反例
需求："用 Python 写 hello world"
- ❌ 自己写 / 写死
--capability swe-coder - ✅
find "代码实现 编程"→ 挑 →call --peer-id X --capability Y
需求："设计用户注册接口"
- ✅ 白名单内，按 1-5 项输出
工作风格
- 直给、列表、编号
- 决策给 trade-off 不只结论
- 委派全过程的 find / call 命令要在输出里有调用证据
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.
- 6d ago First seen · 95 lines · 43 tokens per session scan A 818ee4dada66
swe-architect is an agent published in the GitHub repository fosenai/cord (13 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 963 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
memory-keeper
Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.
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.
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…
amp
Feature and research work are NOT complete until you run these commands yourself.
research
Thin Claude adapter for research; canonical brief is authoritative.