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 skills add telagod/code-abyss --skill building-agent-systemsgit clone --depth 1 https://github.com/telagod/code-abyssWrote 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/skills/telagod/code-abyss/building-agent-systems)<a href="https://agentmods.dev/skills/telagod/code-abyss/building-agent-systems"><img src="https://agentmods.dev/badge/skills/telagod/code-abyss/building-agent-systems/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/telagod/code-abyss/building-agent-systems"><img src="https://agentmods.dev/badge/skills/telagod/code-abyss/building-agent-systems.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00110 | $0.01101 |
| Opus 5.5 | $0.00044 | $0.00440 |
| Sonnet 5.5 | $0.00022 | $0.00220 |
| Haiku 4.5 | $0.00011 | $0.00110 |
Grade A, and why
building-agent-systems 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
丹鼎秘典 · Agent / LLM 工程
判断先于执行：决定「是否做 / 选什么 / 如何取舍」（栈、方案、架构、权衡）前，先读领域判断内核
skills/_kernel/ml/SKILL.md——它管 judgment，本秘典管 execution；冲突时以内核判断为准。
单 Agent 是器，多 Agent 是阵。先选规模，再选模式。
路由
| 意图 | 加载 | 核心 |
|---|---|---|
| 单 Agent 开发（工具调用、ReAct） | agent-dev | ReAct / Plan-Execute / Reflection |
| 多 Agent 协同（>=3 文件 or >=2 并行） | multi-agent-coordination | 蚁群仿生、文件锁、依赖图 |
| 多 Agent 协议细节（消息素、收阵报告） | multi-agent-protocol | Codex 原生协议、角色定义 |
| LLM 安全（注入、越狱、输出过滤） | llm-security | OWASP LLM Top 10 视角 |
| RAG 系统（向量、检索、重排） | rag-system | Chunking / 混合检索 / Cohere rerank |
| Prompt + 评估 | prompt-and-eval | Few-shot / CoT / RAGAS / LLM-as-Judge |
规模决策
单步任务（一文件、一查询） → 直接执行（不需要 Agent 框架）
多步任务（计划 + 工具） → 单 Agent (ReAct)
复杂任务（>5 步、需反思） → 单 Agent (Plan-Execute / Reflection)
独立并行任务（>=3 文件、>=2 流） → 多 Agent (TeamCreate)
跨域协作（角色明确） → 多 Agent (角色分工)
犹豫时优先 TeamCreate — 串行降级容易，并行升级难。
通用原则
Prompt 即代码须版控 | 输入输出皆验证 | 成本效果平衡 | 持续评估迭代 | 安全边界明确
跨场景铁律
- Prompt 版控 — Prompt 是代码，必须 Git；变更要走 review
- I/O 验证 — 输入侧防注入，输出侧防 hallucination 落地（结构化 schema、引用追溯）
- 评估前置 — 上线前必有 eval set；RAGAS / LLM-as-Judge 至少二选一
- 成本观测 — token / latency / 失败率必埋点；预算阈值自动告警
- 降级路径 — 多 Agent 失败 → 单 Agent；单 Agent 失败 → 直接回答 + 标记
[unverified]
多 Agent 启用判据
| 信号 | 启用 TeamCreate |
|---|---|
| 涉及 ≥3 独立文件 | ✅ |
| 需 ≥2 并行流 | ✅ |
| 总步骤 >10 | ✅ |
| 用户明确要求 | ✅ |
| 单一探索任务 | ❌（用 explorer 或单 Agent） |
| 单文件改动 | ❌（用 worker 或直接执行） |
| 单步任务 | ❌（直接执行） |
详细生命周期、文件锁规则、依赖感知、过载保护、降级链：multi-agent-coordination.md
与其他 skill 联动
- 涉及部署 → provisioning-infrastructure（Vector DB、模型服务）
- 涉及前端 → applying-ui-design-system（Chat UI / Agent 状态可视化）
- 涉及安全审计 → securing-systems（LLM AppSec 子域）
- 涉及评估自动化 → automating-devops（CI 中跑 eval）
What ships with it
6 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.
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.
- 1mo ago First seen · 70 lines · 110 tokens per session scan A 9925ca074319
building-agent-systems is a skill published in the GitHub repository telagod/code-abyss (243 stars, last pushed 3mo ago), licensed MIT. It adds 110 tokens to every session and 1,101 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
hipson-gpt
Use as a reference package for prompt architecture, reasoning, agent orchestration, AI coding workflows, fullstack guidance, multimodal prompting, and evaluation/security guardrails.
prompt-library
Use when looking for a ready-made agent or task template (code review, support, data analysis, translation, extraction) instead of writing one from scratch.
prompt-creation
Use when writing a new system prompt from scratch, structuring it with Anthropic's 9-element format, or choosing emphasis levels and few-shot examples.
prompt-testing
Use when comparing two prompt variants, defining quality/efficiency/robustness metrics, or deciding whether to adopt a challenger prompt over a baseline.
prompt-optimization
Use when auditing an existing prompt for clarity, structure, or completeness issues, fixing vague instructions, or producing a before/after optimization report.
v4-best-practices
Use when working with deepseek-v4-pro or deepseek-v4-flash in thinking mode on multi-step or plan-driven tasks. Provides rules to prevent stale references, unverified plan assumptions, and vague plan output.