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 skills/telagod/code-abyss/building-agent-systemsnpx skills add telagod/code-abyss --skill building-agent-systemsgit clone --depth 1 https://github.com/telagod/code-abyssWhat 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 | $0.00110 | $0.01101 |
| Opus 5 | $0.00055 | $0.00550 |
| Sonnet 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 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.
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.
- 2d 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 (239 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 1,101 once invoked, about $0.0006 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 skills, from other repositories
codexkit-api-design-reviewer
Review REST and GraphQL API designs for consistency, usability, and best practices. Covers naming conventions, versioning strategy, error format, pagination, authentication patterns, and breaking change detection. Use when reviewing API specs, designing new APIs, or auditing existing endpoints.
codexkit-change-management-plan
Build change management plans using ADKAR and Kotter's 8-Step framework. Covers stakeholder readiness, communication plans, training schedules, resistance management, and adoption metrics. Use when rolling out new systems, reorganizations, or process changes that affect people.
codexkit-crisis-communication
Draft crisis communication packages including holding statements, stakeholder updates, Q&A documents, and internal briefs. Follows ICS (Incident Command System) communication principles. Use during PR crises, data breaches, product recalls, or any event requiring rapid coordinated messaging.
codexkit-interview-guide-builder
Build structured behavioral interview guides using the STAR method. Map job competencies to interview questions, provide scoring rubrics (1–5), and include follow-up probes and red/green flag indicators. Use when preparing for hiring interviews or standardizing interview practices.
codexkit-legal-due-diligence
Conduct structured legal due diligence for M&A, joint ventures, or investment transactions. Cover all 9 workstreams — Corporate, Contracts, IP, Litigation, Regulatory, Employment, Tax, Environmental, and Data Privacy. Produce a risk matrix with deal-breaker flags and closing conditions. Use when evaluating a target or…
codexkit-a-b-test-planner
Design rigorous A/B test plans with hypothesis, sample size calculation, Minimum Detectable Effect (MDE), randomization strategy, and decision rules. Includes guardrail metrics and rollout playbook. Use when planning product experiments, conversion optimization, or data-driven feature decisions.