SkillYard AGENTS.md

A set of instructions for coding agents working on the SkillYard project. It defines implementation boundaries, architecture decisions, testing expectations, and when to ask for approval.

In plain words
What is it for?
It is for guiding feature work, tests, architecture changes, commits, and phase acceptance in the SkillYard repository.
Why use it?
It prevents speculative fixes, duplicate implementations, and changes that go beyond the project's current product contract or plan.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/reyyang/skillyard/agents-md
Clone the repo
git clone --depth 1 https://github.com/ReyYang/SkillYard

Made for: Codex, OpenCode.

Per session 925 This file is loaded in full into every session.
When invoked 925 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00925 $0.00925
Opus 5 $0.00463 $0.00463
Sonnet 5 $0.00185 $0.00185
Haiku 4.5 $0.00093 $0.00093

Measured 2d ago against content hash aa03e8ee7cf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

SkillYard 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 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.

AGENTS.md · 45 lines

What it actually says

SkillYard 实施约束

SkillYard 1.0 优先保证真实用户路径,而不是理论完备性。任何修复如果需要扩大领域模型或生命周期协议,必须首先证明它违反了已承诺的 Product Contract,并证明它能够在正常生产路径中自然发生。否则应记录为 Future Consideration,而不是进入当前实现。 当发现一个新的问题时,默认假设它“不应该修”,而不是默认假设“应该修”。只有在证据足以推翻这个假设时,才允许进入实现。

本文件约束后续在本仓库工作的编码 Agent。产品行为仍以 docs/1.0-product-contract.md 为准,实施顺序以 docs/plans/0001-skillyard-1.0-implementation.md 为准。

单一实现原则

  • 1.0 中每项生命周期能力只能有一套 canonical domain model、持久化协议和生产入口。
  • 不得自行增加 v2legacynext 等并行实现,也不得为了保留本阶段刚写出的代码而维护两套状态机。
  • 当前实现不能覆盖已确认需求时,先停止编码,说明“原地重构、替换实现、缩小范围”三种选择及成本;只有用户明确确认后才能改变架构边界。
  • 兼容层只能用于已经核验存在的真实用户数据或已发布契约。不能把未发布的开发中间状态推定为兼容要求。

阶段边界

  • 只实现当前计划阶段明确列出的行为,不提前建立下一阶段的数据模型、Adapter 或扩展点。
  • 开始一个阶段前,先固定该阶段的完整技术实现图,包括唯一领域模型、持久化协议、文件系统生效点、恢复方向、复用能力和文件职责。切片用于验证这张实现图中的不同产品行为,不能用于边写边发现第二套架构。
  • 每个切片必须从用户可观察的公开 seam 开始,以一个失败测试进入,以该测试通过结束。
  • 一个切片只解决一个产品行为,并独立 commitpush
  • 代码规模只作为审查信号,不是机械停止线。当实现范围明显超出阶段技术图时,必须解释增加的职责,并审查是否出现错误抽象、水平切片或重复能力;不能为了降低行数机械拆文件。
  • “功能完整”指计划中的用户主流程和基础能力全部可用,不等于穷尽所有理论边界。新增防御协议前必须说明 1.0 用户如何实际触发该风险及实现成本;同一用户恶意并发、主动追逐私有临时名等低概率对抗场景默认不扩张 1.0。
  • 阶段完成后必须完成该阶段验收并报告结果。只有计划明确设置人工确认点、命中架构变更门或缺少外部授权与环境条件时才停止;否则可以继续下一个已批准阶段,但同样要先固定完整技术实现图。

架构变更门

出现以下任一情况时必须停止,并在继续修改前取得用户确认:

  • 新增第二套 Plan、Transaction、Journal 或恢复协议;
  • 新增带版本后缀的领域类型、表、migration 或模块;
  • 为兼容未核验的本地状态而保留旧生产入口;
  • 当前阶段需要修改下一阶段的产品边界;
  • 测试只能通过调用生产入口不会调用的私有步骤;
  • 独立审查发现当前切片无法通过局部修复满足产品契约。

验收纪律

  • 主验收测试只通过 SkillYardApplication、typed Tauri command/client、真实临时文件系统和重启后的持久状态观察行为。
  • 私有函数测试只能补充算法边界,不能代替真实生产入口测试。
  • 提交前检查 diff 范围、相关测试、类型检查和格式;阶段完成时运行全量测试、clippy -D warnings、生产构建和独立代码审查。

测试条件

  • 优先使用 tart 在沙箱 VM 中测试。
Changes

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.

  1. 2d ago First seen · 45 lines · 925 tokens per session scan A aa03e8ee7cf7

Subscribe to this mod's changes

SkillYard AGENTS.md is an instructions file published in the GitHub repository ReyYang/SkillYard (2 stars, last pushed 6d ago), licensed MIT. It adds 925 tokens to every session, about $0.0046 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 2026-08-31.

Related

Other instructions, from other repositories

siyuan AGENTS.md

AGENTS.md instructions for siyuan-note/siyuan, covering agents.md, 1. non-negotiable constraints, do not hand-edit, verification and prohibited operations and 2. project-specific rules.

siyuan-note/siyuan · 4,668 tokens

veritas-kanban AGENTS.md

Instructions for BradGroux/veritas-kanban, covering agents.md — canonical agent instructions for veritas kanban, runtime requirements, repository layout, essential commands and install.

BradGroux/veritas-kanban · 7,081 tokens

apm python.instructions.md

Python development guidelines.

microsoft/apm · 78 tokens

mcp-server-excel coverage-prevention-strategy.instructions.md

Instructions for sbroenne/mcp-server-excel, covering generated surface coverage, contract change workflow, required checks and common incomplete changes.

sbroenne/mcp-server-excel · 396 tokens

mcp-server-excel mcp-llm-guidance.instructions.md

Instructions for sbroenne/mcp-server-excel, a project described as: Automate real Microsoft Excel with AI via MCP Server or CLI — Power Query, DAX, VBA, PivotTables, charts, and 326 operations.

sbroenne/mcp-server-excel · 254 tokens

apex-accelerator no-interactive-shell.instructions.md

Prevents interactive shell prompts and long-output terminal replays from being injected into chat. Forbids -i flags on mv/rm/cp, read -p, and confirm prompts (incl. inside bash -c '...'). Pipe long output to files. Scoped to chat-context-loaded files; skill references/ and templates/ are exempt because they hold…

jonathan-vella/apex-accelerator · 1,396 tokens