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/tianemon/easymint/dev-docsnpx skills add tianemon/EasyMint --skill dev-docsgit clone --depth 1 https://github.com/tianemon/EasyMintWhat 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 | $0.00083 | $0.01352 |
| Opus 5 | $0.00042 | $0.00676 |
| Sonnet 5 | $0.00017 | $0.00270 |
| Haiku 4.5 | $0.00008 | $0.00135 |
Grade A, and why
dev-docs 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 yesterday.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Docs — 项目文档记录规范
开发期维护项目文档时按本规范执行。极简项目(单文件/无依赖)不建文档体系;有文档体系的项目按本规范执行。
文档分层
docs/开发记录.md 导航页(唯一真相源):头部「当前进度快照」+「开发记录索引」
docs/开发记录/<日期>.md 按日期分文件的进度明细(只增不改,带提交 hash)
CHANGELOG.md 正式发布日志(Keep a Changelog,只记用户可见变更)
docs/技术架构.md 架构设计(只追加,记录技术选型与关键决策)
分工:导航页管「现在在哪」,明细管「每天发生了什么」,CHANGELOG 管「发布了什么」,技术架构管「系统怎么设计」——四者不重复记录同一内容。
docs/开发记录.md(导航页)
本文件是项目进度与交接的唯一真相源,会话交接时更新。两部分:
头部「当前进度快照」
记录当前状态,每次会话交接时更新(本区可改):
### 当前版本
- **vX.Y.Z**(日期发布:一句话变更摘要)
### 最近工作
**日期 变更主题**(详见 docs/开发记录/<日期>.md):
- 本次变更要点(2-4 条,可追溯明细)
### 接下来安排
1. 未完成的待办(按优先级)
- 「最近工作」保留最近 1-2 次会话即可,更早的折叠到下方时间线或由明细承接
- 更新时机:会话结束时(交接给下一次会话)、每次发版后
- 新会话开始时先读本文件头部快照,了解当前状态再开工
开发记录索引
日期 → 日志文件映射(按日期降序),每天日志独立存 docs/开发记录/<日期>.md——按需读取,避免单文件无限膨胀:
| 日期 | 记录 |
|------|------|
| 2026-08-19 | 27. 移除请求超时 & 会话卡死修复(2026-08-19,v0.10.2) |
- 每次新建当天日志时,在索引表加一行(编号递增)
- 同一天多条记录合并为一行(用分号分隔)
docs/开发记录/<日期>.md(按日期明细)
- 文件名如
2026-08-19.md,记录当天项目变动 / 用户决策 / 实现详录 - 只增不改:当天记录追加到当天文件,不覆盖历史;已写内容不修改
- 每条记录带日期 + 提交 hash 关联,方便回溯(如「2026-08-19 移除请求超时(commit c51e9e2)」)
- 记录内容:用户需求与决策、实现方案要点、踩坑与根因、发布记录
- 写入时机:每个任务完成、每个阶段切换时追加
CHANGELOG.md(正式发布日志)
遵循 Keep a Changelog 规范,只记录 release 的用户可见变更:
- 日常变更先记入
[Unreleased]区块,发版时整理成版本条目 - 版本条目格式:
## vX.Y.Z (日期) — 变更主题,下分### Added / Changed / Fixed / Removed(按需) - 只写用户能感知的变更(功能/修复/交互/性能),不写内部实现细节
- 与
docs/开发记录.md分工:CHANGELOG 面向用户看版本变化,开发记录面向开发看过程 - 发版流程:① 更新版本号 + 整理 CHANGELOG 条目 → ② 打 tag → ③ 推送触发 CI 自动 Release
docs/技术架构.md(架构设计)
记录系统架构与关键决策,只追加、不重写:
- 记录内容:系统架构、数据模型、模块划分、关键设计决策(含为什么这么选)
- 每次架构级变更追加一个新章节(如「设备互联(v0.6.6)」「会话隔离(v0.6.5)」),标注版本
- 不记录:代码能自解释的细节、临时方案、一次性决策(这些进开发记录明细)
- 发现过时描述(如已删除的机制仍被引用)时主动修正,避免误导
- 新会话涉及架构问题时先读本文件再动手
通用规则
- 文档用中文命名,放入
docs/目录 - 增量更新优先:追加新内容直接写;修改或删除已有内容,先向用户列出要改的部分确认
- 写文档时所有占位符({{PROJECT_NAME}}、[待填写])必须替换为实际内容,禁止留空
- 归档:定稿且不再维护的方案文档移入
docs/archive/,当前文档区只保留有效文档
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.
- yesterday First seen · 95 lines · 83 tokens per session scan A 61190fefbf2f
dev-docs is a skill published in the GitHub repository tianemon/EasyMint (21 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 1,352 once invoked, about $0.0004 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
source-command-audit-whitepapers
Audit version freshness, FR/EN parity, and metadata quality of all whitepapers and recap cards.
self-assessment
Interactive skill assessment with personalized learning path generation.
source-command-track-mentions
Search for new online mentions of the Claude Code Ultimate Guide or Florian Bruniaux's public project portfolio and update the relevant tracker.
guide-recap
Transform CHANGELOG entries into social content (LinkedIn, Twitter/X, Newsletter, Slack) in FR + EN. Use after releases or weekly to generate ready-to-post content from guide updates.
source-command-audit-prose
Add descriptive prose to bare sections in whitepapers (FR + EN) using 9 parallel agents.
source-command-methodology-advisor
Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.