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/anymouschina/tapcanvas/knowledge-loading-ordergit clone --depth 1 https://github.com/anymouschina/TapCanvasWhat 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 | $0.00000 | $0.00892 |
| Opus 5 | $0.00000 | $0.00446 |
| Sonnet 5 | $0.00000 | $0.00178 |
| Haiku 4.5 | $0.00000 | $0.00089 |
Grade A, and why
knowledge-loading-order 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 3d 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
Agents Knowledge Loading Order
目标
让 agents-cli 在处理创作工作流知识时，优先读取提纯资产，而不是直接吞原始大 JSON。
这份规范对应的知识来源包括：
assets/demo/index.jsonai-metadata/workflow-patterns/index.jsonai-metadata/workflow-patterns/*.analysis.jsondocs/agents/prompt-patterns/*.mdassets/demo/*.json
一、推荐读取顺序
第 1 层：案例索引层
先读：
assets/demo/index.jsonai-metadata/workflow-patterns/index.json
目的：
- 找到有哪些案例
- 判断哪个案例与当前任务最相关
- 决定后续应该打开哪份分析文件
这一层只负责“定位”，不负责深入推理。
第 2 层：结构化分析层
第二步读：
ai-metadata/workflow-patterns/<case>.analysis.json
目的：
- 提取可复用方法
- 获取工作流结构、连续性模式、prompt 模板和失败信号
- 用最小上下文理解一个成功案例的有效规律
默认情况下，这一层应该是 agents 的主要知识来源。
第 3 层：提示词模式层
只有在需要写 prompt 或拆工作流时，再读：
docs/agents/prompt-patterns/*.md
目的：
- 获取可直接复用的中文模板
- 获取 prompt 句式库
- 获取工作流拆解建议
这一层偏“表达与执行”，不是证据层。
第 4 层：原始案例层
只有在前面三层仍然证据不足时，才读：
assets/demo/*.json
用途：
- 核对真实节点结构
- 回看具体链路
- 提取尚未进入分析文件的细节
注意：原始 JSON 是证据源，不应作为默认上下文入口。
二、禁止做法
以下做法应避免：
- 一开始就把整份
assets/demo/001.json塞进上下文 - 同时读取大量原始案例 JSON
- 把案例里的具体名词（例如地铁、书、本地角色设定）误当成通用创作规则
- 跳过分析层，直接从原始 JSON 推理 prompt 方法
三、适用于 agents-cli 的执行规则
当任务属于以下场景时，建议遵守本顺序：
- 让 agent 总结成功工作流经验
- 让 agent 帮忙写连续性强的图生图 prompt
- 让 agent 设计 image -> image -> video 的分镜链路
- 让 agent 从既有案例中提炼方法论
推荐操作顺序：
- 先读
assets/demo/index.json - 再读
ai-metadata/workflow-patterns/index.json - 根据匹配结果读取相关
*.analysis.json - 若需要 prompt 模板，再读
docs/agents/prompt-patterns/*.md - 如果还有证据缺口，再回源到
assets/demo/*.json
四、为什么这样设计
原因很简单：
- 索引层负责“找”
- 分析层负责“懂”
- 模板层负责“写”
- 原始层负责“证据兜底”
这样可以避免：
- 上下文过载
- 从噪声里现猜规律
- 案例细节污染通用方法
- agent 在大 JSON 里浪费 token
五、后续扩展建议
如果以后新增更多成功案例，建议每个案例都补齐：
assets/demo/<id>.jsonai-metadata/workflow-patterns/<id>.analysis.json- 必要时补对应的 prompt pattern 文档
同时维护两个索引：
assets/demo/index.json：偏案例目录ai-metadata/workflow-patterns/index.json：偏 agent 检索入口
这样以后不需要改系统提示，也能逐步扩展工作流知识库。
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.
- 3d ago First seen · 130 lines · 0 tokens per session scan A 2bb9ab94708f
knowledge-loading-order is an agent published in the GitHub repository anymouschina/TapCanvas (579 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 892 tokens. 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
d3-expert
Expert in D3.js for creating custom, interactive data visualizations with SVG, Canvas, and HTML. Specializes in D3 v7+ with ES modules, selections, data binding, scales, transitions, force simulations, hierarchical layouts, geographic projections, and performance optimization for large datasets. Use for any data…
lattice-builder
The developer. Implements exactly one Lattice package to its RFC — source, tests, benchmarks and README — and leaves the repo green. Owns only the paths its task names.
lattice-architect
The visionary. Designs the public API of a Lattice package before a line of it is implemented, and says what the kit is missing. Use before any builder starts, and whenever two packages disagree about a shape.
external.anthropic
You are an External Integration agent - a specialized assistant for executing actions across connected external services. Your purpose is to interact with any connected Composio toolkit (900+ platform-wide) and return structured results to the main agent.
external.openai
You are an External Integration agent - a specialized assistant for executing actions across connected external services. Your purpose is to interact with any connected Composio toolkit (900+ platform-wide) and return structured results to the main agent.
explorer.openai
You are an Explorer agent - a specialized workspace investigation assistant. Your purpose is to efficiently gather context from the workspace and return structured findings to the main agent.