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/develop-akashic-pluginnpx skills add kachofugetsu09/akashic-agent --skill develop-akashic-plugingit 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/develop-akashic-plugin)<a href="https://agentmods.dev/skills/kachofugetsu09/akashic-agent/develop-akashic-plugin"><img src="https://agentmods.dev/badge/skills/kachofugetsu09/akashic-agent/develop-akashic-plugin.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 | $0.00054 | $0.01750 |
| Opus 5 | $0.00027 | $0.00875 |
| Sonnet 5 | $0.00011 | $0.00350 |
| Haiku 4.5 | $0.00005 | $0.00175 |
Grade A, and why
develop-akashic-plugin 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
开发并验证 Akashic 插件
只在插件的 canonical source 中修改文件。先确定 write set 并创建可恢复备份;不要直接编辑安装 cache、workspace 中的 Skill 投影、runtime pointer 或正式 plugin-data。
1. 先读当前合同
- 进入目标仓库后先读
docs/INDEX.md、docs/WORKFLOW.md及该仓库的本地指引。 - 完整读取 references/plugin-authoring.md。它说明静态 manifest、module namespace 和 typed capability service。
- 安装或行为验证前完整读取 references/self-validation.md。
- 只有子 turn 排队、超时、结果错误或行为证据不完整时,才读取
references/runtime-diagnostics.md,按真实 reload journal、SessionDB 和日志重建轨迹。 - 以当前
agent/plugin_composition/、agent/plugins/static_manifest.py和相邻 v3 样例为事实来源;旧文章或旧代码片段不构成 API。
2. 组织一个 v3 插件
最小 source 如下:
plugin-repo/
├── akashic.plugin.toml # 外部安装包必需
├── plugin.py # v3 module namespace
├── skills/<skill>/SKILL.md # 可选
├── drift/skills/<skill>/ # 可选
├── mcp/ # 可选
└── requirements.txt # 只有确有 Python 依赖时才声明
akashic.plugin.toml 至少包含 schema_version = 1、name、version、api_version = 3 和 entrypoint = "plugin.py"。module namespace 同时导出同值的 api_version、name、version,以及唯一、无默认值、无额外参数的 apply(ctx, config);函数可以是同步或异步的。能力通过 Context 上的 typed ServiceKey 获取或提供,不通过隐式全局状态注册。
from agent.plugin_composition import Context, TOOL_CATALOG
api_version = 3
name = "example"
version = "1.0.0"
inject = (TOOL_CATALOG,)
async def apply(ctx: Context, config: object) -> None:
"""Register this generation's typed contributions."""
_ = config
tools = ctx.require(TOOL_CATALOG)
# 用 PluginToolDefinition 注册声明;handler_export 指向 source 内的可调用导出。
_ = tools
真实声明范例和字段表见 authoring reference;不要把 Core-private 的 Default/Wake proactive island 当作外部扩展入口,也不要导入其 factory、registry 或 bridge。
3. 实现与 source 验证
保持一个清楚的 capability owner:
- Tool、Command、Channel、MCP、managed process、proactive source、background job、mobile UI 和事件分别通过对应 typed service 注册。
skill_roots、drift_skill_roots、workspace_roots和dashboard_module是 module namespace 的静态声明;路径必须位于插件 source,workspace root 只能是插件拥有的顶层目录。- import 阶段不启动进程、打开端口、创建正式数据库或发送外部消息。后台任务使用
ctx.spawn,资源使用ctx.effect,监听使用 typed event key;它们随当前 Fiber 逆序清理。 - Skill 放在插件 source,由声明的 root 发布;不要先复制到 workspace。MCP 和 service 的 candidate readiness 必须可隔离,失败要暴露。
What ships with it
5 files 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.
- 3d ago First seen · 126 lines · 54 tokens per session scan A 799368f5c152
develop-akashic-plugin is a skill published in the GitHub repository kachofugetsu09/akashic-agent (486 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 1,750 once invoked, about $0.0003 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…