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/kachofugetsu09/akashic-agent/create-drift-skillnpx skills add kachofugetsu09/akashic-agent --skill create-drift-skillgit clone --depth 1 https://github.com/kachofugetsu09/akashic-agentWrote 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/kachofugetsu09/akashic-agent/create-drift-skill)<a href="https://agentmods.dev/skills/kachofugetsu09/akashic-agent/create-drift-skill"><img src="https://agentmods.dev/badge/skills/kachofugetsu09/akashic-agent/create-drift-skill.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 5.1 | $0.00047 | $0.02101 |
| Opus 5 | $0.00023 | $0.01051 |
| Sonnet 5 | $0.00009 | $0.00420 |
| Haiku 4.5 | $0.00005 | $0.00210 |
Grade A, and why
create-drift-skill 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 6d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
创建 Drift Skill
目标
把空闲时仍愿意再次做的小活动沉淀到 skills/<skill_name>/SKILL.md。
本轮处于设计期,只负责给未来的 Drift 写一份可选择的活动说明书,不执行新活动本身。
未来如何被选择
新 skill 不会因为文件创建成功就立刻运行,也没有独立的定时触发器。
当前 create-drift-skill
└─ 写入新 SKILL.md
└─ 从下一轮 Drift 起进入候选列表
├─ runtime 展示 name、description 和过去状态
├─ agent 结合空闲时的意图、环境和前情自由选择
└─ 选中后才读取正文并执行活动
因此,frontmatter 的 description 不只要说明“能做什么”,还要说明“什么情况下可能想选它”。
正文则说明选中以后如何完成一次最小活动。
何时使用
- 发现一种以后还可能想做的活动
- 近期多轮总在做相似的小动作,开始显露出一个值得独立发展的活动
- 此刻确实想做一件事,但现有 skill 都不能自然表达它
- 现有 drift skill 太旧,需要补充流程或 working files
- 不要因为“应该扩充能力”而强行创建;没有自然想法时可以做别的或休息
工作流
- 先说明为什么以后还会想做这件事,以及什么空闲情境下可能会选择它;再回答“连续运行三次后,会积累或改变什么”。如果答案是什么也不会改变,就不要创建。
- 从这个活动形成一个不同于
create-drift-skill的目标名称,再检查skills/<skill_name>/是否已存在。不要把元 skill 自己当成目标 skill。 - 读取目标的
SKILL.md;如果已存在就在原基础上更新,不存在再创建。 - 只把可长期复用、可独立闭环的小活动沉淀成 drift skill;一次性进展写入
finish_drift,不要创建新 skill。 - 先定义“何时可能选择”和一次 Drift run 的最小闭环,再决定是否需要脚本。
SKILL.md顶部 frontmatter 至少包含:
---
name: <skill_name>
description: <做什么,以及什么空闲情境下适合选择>
---
- 正文只写未来选中后真正需要的最小流程,避免空泛模板。
值得成为 skill 的最低条件
- 每轮至少产生一种真实变化:形成新的理解、留下可继续使用的素材、推进一个兴趣、改善已有能力,或为用户准备以后可能有价值的东西。
- 活动来源至少有一个实际依据:用户兴趣、近期行为、自我观察,或当下确实想再次进行的动作。
- 它必须区别于已有能力。单纯“不打扰”“安静待着”“等待一会儿”已经由
idle_drift表达,不要包装成新 skill。 - 不要求每轮推送用户;内部成长和素材积累也算变化,但必须能说清留下了什么。
message_push是 fire-and-forget。新 skill 可以发消息或轻问题,但发送成功就必须自行闭环,不能把等待回答、没有回答或下轮追问当作状态。
如果活动需要了解用户兴趣,可以在设计期查找足以确定方向的上下文。但不要提前执行新活动:未来运行所需的检索、检查和工具调用,应写进新 skill 的流程,留到它以后真正被选择时执行。
搜索只服务于会改变目标名称、选择情境或单次闭环的信息。现有理解已经足以写出可修改的初版时,直接落盘;证据不足可以成为新 skill 未来运行时需要验证的内容。
状态模型
新 drift skill 必须使用 runtime 统一状态,不要自行维护并行状态文件:
drift run
├─ scratchpad_update
│ └─ 自然语言说明下次从哪里继续
├─ cursor_update
│ └─ 结构化游标,供脚本或下轮流程直接决定下一步
└─ journal_append
└─ append-only 记录已经完成、问过、审计过、生成过的事实
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.
- 6d ago First seen · 164 lines · 47 tokens per session scan A 018bdc129a01
create-drift-skill is a skill published in the GitHub repository kachofugetsu09/akashic-agent (488 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 2,101 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…