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/hwyd/ai-mind/ai-mind-implementation-readernpx skills add HWYD/ai-mind --skill ai-mind-implementation-readergit clone --depth 1 https://github.com/HWYD/ai-mindWrote 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/hwyd/ai-mind/ai-mind-implementation-reader)<a href="https://agentmods.dev/skills/hwyd/ai-mind/ai-mind-implementation-reader"><img src="https://agentmods.dev/badge/skills/hwyd/ai-mind/ai-mind-implementation-reader.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 | $0.00101 | $0.01732 |
| Opus 5 | $0.00051 | $0.00866 |
| Sonnet 5 | $0.00020 | $0.00346 |
| Haiku 4.5 | $0.00010 | $0.00173 |
Grade A, and why
ai-mind-implementation-reader 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 4d 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Mind Implementation Reader
定位
只服务于 AI Mind 项目内部的“版本实施代码阅读”。当用户想在某个版本、Step 或功能实现完成后快速读懂真实代码如何跑起来时,使用本 Skill。
只解决四件事:
- 给出版本实施修改代码的阅读顺序。
- 讲解关键文件 / 函数。
- 梳理主执行流程。
- 用大白话解释实现。
默认不做
默认不要做以下事情:
- 不做 code review。
- 不提重构建议。
- 不修改代码。
- 不写测试。
- 不写博客。
- 不整理面试话术。
- 不做 Spec / Plan / Tasks 差异分析。
- 不做完整架构评审。
- 不扫描整个仓库。
- 不扩大成通用项目 Skill。
如果用户明确要求 code review、博客、面试话术、重构建议或 Spec 差异分析,说明这已经超出本 Skill 默认范围,并按用户的新任务另行处理。
信息来源优先级
真实代码是最高优先级。按以下顺序建立事实:
git diff- changed files
- 实际源码
- 当前分支最近提交
- specs、plans、tasks、docs、version notes
Specs、plans、tasks、docs、version notes 只能作为辅助背景,不能替代真实代码。不要脑补不存在的文件、函数、类型、执行流程或架构决策。
如果任务涉及“版本实现”或“某个 Step 实现”,必须定位并阅读 specs/<version>/spec.md。先用它确认该版本的目标、非目标、能力边界和关键术语,再回到真实代码梳理实现主线。
如果已经知道当前版本或 Step,优先补读与之对应的 specs/<version>/tasks.md;它只用于帮助判断这次实现大致覆盖了哪一段能力,不替代真实代码阅读。
默认执行步骤
当用户没有指定版本范围时,先轻量查看本次实现概况:
git status --short
git diff --stat
git diff --name-only
git log --oneline -n 5
根据变更文件判断本次实现涉及哪些模块。不要默认深读所有文件,只挑出能解释主流程的关键文件。
如果用户指定了版本、Step、commit、分支、PR、文件列表或 diff,以用户指定范围为准;仍然优先回到真实代码确认。
如果确认这是一轮版本实现阅读,默认步骤改为:
- 先定位版本范围。
- 先读
specs/<version>/spec.md。 - 再看
git diff、changed files、最近提交和实际源码。 - 最后抽出 5 到 8 个关键文件组织阅读顺序。
文件选择规则
只选择对理解主流程有价值的关键文件,不要因为某个文件发生变更就机械列入阅读顺序。
优先选择:
- 用户入口:页面、命令入口、API route。
- 后端执行路径:runtime、graph、manager、orchestrator、service。
- 核心契约:types、schema、runtime artifact、stream chunk、state model。
- Tool / Agent 实现:tool runtime、sub-agent、controlled loop、agent definition。
- 前端消费:reducer、renderer、panel、status component。
- 持久化:Prisma schema、database access、checkpointer、memory state。
- 测试或文档:只有在它们能帮助理解实现时才阅读。
阅读顺序规则
阅读顺序从“入口”到“执行”再到“展示”。优先按 AI Mind 常见链路组织:
用户操作 / 页面 / 命令
-> API route
-> runtime / graph / manager / orchestrator
-> tool / agent / service
-> type / state / protocol
-> stream / artifact output
-> frontend reducer / renderer / panel
-> persistence if involved
每个关键文件都要说明:
- 为什么它排在这个阅读位置。
- 它在主流程里负责什么。
- 阅读时重点看什么。
阅读方法
What ships with it
1 file 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.
- 4d ago First seen · 202 lines · 101 tokens per session scan A 94eb6d07ae75
ai-mind-implementation-reader is a skill published in the GitHub repository HWYD/ai-mind (19 stars, last pushed 3d ago), licensed MIT. It adds 101 tokens to every session and 1,732 once invoked, about $0.0005 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
anneal
Use when the user wants to systematically fix AI code slop — duplicated logic, over-engineering, silent error swallowing, convention drift, cargo-cult patterns, and other LLM-introduced architectural decay — over a specified duration.
new-service
Add a new service to Harbor — scaffold the compose config, environment variables, metadata, documentation, and cross-service integrations. Use this skill whenever the user wants to add a new service to Harbor, integrate a new tool/app/model server, create a compose configuration for a new project, or onboard any…
facts-implement
Operate on @spec facts — implement them in code, then tag @implemented. Use when asked to implement facts, implement the spec, build from the fact sheet, make facts true, or work through unimplemented requirements.
new-boost-module
Create new Harbor Boost modules — the Python plugins that run inside Harbor's LLM proxy. Use this skill whenever the user wants to build a Boost module, write a custom module for Harbor Boost, add a new feature to the Boost proxy pipeline, or create any kind of middleware that transforms, augments, or intercepts LLM…
boost-modules
Skill "boost-modules" from av/harbor, covering harbor boost custom modules, module structure, quick reference, output methods and stream text to client.
bugbash
Systematically explore and test any software project (CLI, API, Backend, Library, etc.) to find bugs, usability issues, and edge cases. Produces a structured report with full reproduction evidence (exact commands, inputs, logs, and tracebacks) for every issue.