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 instructions/hwyd/ai-mind/agents-mdgit 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/instructions/hwyd/ai-mind/agents-md)<a href="https://agentmods.dev/instructions/hwyd/ai-mind/agents-md"><img src="https://agentmods.dev/badge/instructions/hwyd/ai-mind/agents-md.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 | $0.03170 | $0.03170 |
| Opus 5 | $0.01585 | $0.01585 |
| Sonnet 5 | $0.00634 | $0.00634 |
| Haiku 4.5 | $0.00317 | $0.00317 |
Grade A, and why
ai-mind AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
Version Spec Workspace Continuity (Mandatory)
- 同一未收口版本只允许一个 canonical
specs/工作区。当前版本尚未完成 release closing / merge，尤其代码或规格仍有未提交变更时，所有需求、方案、冲突决策和实现任务 MUST 继续写入.specify/feature.json指向的当前目录。 - 禁止因为返工、主题变化或方案冲突创建
vX.Y.Z-1-*、vX.Y.Z-2-*等 sibling spec directory。只有用户明确声明独立 follow-up，或基准版本已经 release closing 并进入新的开发窗口，才允许创建挂靠目录。 - 新决定覆盖旧决定时，必须在同一 canonical 工作区更新
spec.md、plan.md、tasks.md、data-model.md、contracts/和decisions.md（如存在），删除、改写或标记 superseded 的旧决策；不要通过新目录并存两套事实。 - 运行
speckit-specify、speckit-plan、speckit-tasks、speckit-implement、speckit-analyze或speckit-converge前，先读取.specify/feature.json和当前 managed plan 指针；同一 semver 已有 canonical directory 时 MUST 复用它。需要新目录时，必须先取得用户对“独立 follow-up”的明确授权并说明边界。
项目定位
AI Mind 是一个按版本持续演进的 AI Native 工程项目。
它不是一次性做完的产品，而是一套逐步生长的 Runtime Skeleton。
建议始终按这条主线理解项目演进：
- 本地聊天闭环
- 结构化流式协议
- Tool Calling
- Multi-Tool Runtime
- Skill Runtime
- MCP 能力接入
- Agent Runtime
- 持久化与数据层
- 更完整的生产化能力
事实来源优先级
涉及版本实现、架构边界或阶段验收时，按下面顺序判断事实：
- 用户明确指定的版本、Step、文件或验收要求
- 当前代码、测试与运行脚本
.specify/memory/constitution.md- 当前 feature / version 对应的
specs/ docs/adr/与docs/architecture/README.md、docs/versions/、docs/releases/、docs/tasklists/private-folder/仅在用户明确要求、或需要回看草稿 / 历史过程 / 个人内部材料时读取
说明：
specs/是 Level C / Level D 变更的正式 AI coding 工作区，承接 spec / plan / tasks / acceptance / decisions；版本工作区目录优先采用v0.4.10-feature-slug这类真实 semver 前缀命名。挂靠规格只有在基准版本 release closing 后或用户明确授权独立 follow-up 时才可用，规则见docs/architecture/spec-directory-naming.md。docs/adr/和docs/architecture/是长期架构约束区，不只是展示文档。docs/versions/、docs/releases/、docs/tasklists/是公开展示区，不是默认开发任务源。private-folder/是草稿、历史、个人内部材料和博客 / 面试素材区，不是默认开发事实源。- tasklist 的
[x]是开发记录，不单独构成完成证据；仍要看 spec、实现、测试和实际 diff。
开始大改前先读什么
如果任务涉及版本规划、架构调整、运行时改动或能力扩展，先读：
.specify/memory/constitution.md- 当前版本或能力对应的
specs/ README.md- 如果是架构决策或跨边界改动，读
docs/adr/和docs/architecture/ai-coding-workflow.md - 如果用户明确要求回看草稿、历史过程、博客素材或个人内部材料，再读
private-folder/
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 · 189 lines · 3,170 tokens per session scan A 619bc18b53fa
ai-mind AGENTS.md is an instructions file published in the GitHub repository HWYD/ai-mind (18 stars, last pushed 8d ago), licensed MIT. It adds 3,170 tokens to every session, about $0.0158 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 instructions, from other repositories
claude-scientific-writer AGENTS.md
AGENTS.md instructions for K-Dense-AI/claude-scientific-writer, covering claude agent system instructions, core mission, critical: real citations only & diverse referencing policy, critical: parallel web search policy and critical: save all research results to sources folder.
claude-scientific-writer CLAUDE.md
Claude Code instructions for K-Dense-AI/claude-scientific-writer, covering claude agent system instructions, core mission, critical: real citations only & diverse referencing policy, critical: parallel web search policy and critical: save all research results to sources folder.
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
superpowers-reasonix AGENTS.md
Instructions for christopherarter/superpowers-reasonix, covering project guidance, skills — stop. load a skill before you act, red flags — these thoughts mean stop. you are rationalizing and priority.
unreal-mcp-additional-tools CLAUDE.md
Claude Code instructions for nodormu/unreal-mcp-additional-tools, covering claude.md, what this is, commands, architecture and transports (src/transports/).
vvvv-skills CLAUDE.md
Claude Code instructions for tebjan/vvvv-skills, covering vvvv gamma, when to patch vs code, core concepts, live environment and important conventions.