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 skills add kachofugetsu09/akashic-agent --skill skill-installergit 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/skill-installer)<a href="https://agentmods.dev/skills/kachofugetsu09/akashic-agent/skill-installer"><img src="https://agentmods.dev/badge/skills/kachofugetsu09/akashic-agent/skill-installer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kachofugetsu09/akashic-agent/skill-installer"><img src="https://agentmods.dev/badge/skills/kachofugetsu09/akashic-agent/skill-installer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00118 | $0.01692 |
| Opus 5.5 | $0.00047 | $0.00677 |
| Sonnet 5.5 | $0.00024 | $0.00338 |
| Haiku 4.5 | $0.00012 | $0.00169 |
Grade A, and why
skill-installer 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
安装、更新与卸载 Akashic 技能(Skill)
Akashic 的 skills 插件按四层来源热扫描技能,普通技能不需要编写或安装插件,把含 SKILL.md 的目录放入本地技能目录即可立即被 load_skill 热读取。
1. 四层来源与优先级(高 → 低)
| 优先级 | 来源 (source) |
目录路径 | 适用场景 |
|---|---|---|---|
| 1(最高) | workspace |
$AKASHIC_WORKSPACE/skills/<skill-name>/SKILL.md |
默认安装位置。随工作区持久化,容器/服务重启后不丢失 |
| 2 | user |
~/.akashic/skills/<skill-name>/SKILL.md |
宿主用户级共享技能(注意容器部署时需确认 HOME 是否挂载) |
| 3 | builtin |
<Core 根>/skills/<skill-name>/SKILL.md |
随 Akashic Core 仓库发布的内置通用技能 |
| 4(最低) | plugin |
插件 INSTALLED_ASSETS.register 声明的 skills/ |
与特定插件工具强绑定的随包技能(需走 plugin-system 安装) |
- 同名覆盖:高层同名技能静默覆盖低层;目录名
<skill-name>即技能的唯一标识(对应load_skill(skill="<skill-name>"))。 - 热加载机制:
SkillCatalogParser按目录项与SKILL.md的(mtime, size)自动失效缓存。复制或修改文件后,无需重启服务或重装插件,当轮即可直接调用load_skill(skill="<skill-name>")验证。
2. 确定工作区技能目录
优先使用环境变量 $AKASHIC_WORKSPACE/skills;若当前 Shell 未注入该变量,从提示词的「工作区 → 根目录」或运行进程参数 --workspace 取得准确路径并设置变量。无法确定时先询问,不猜测其他实例的目录:
: "${AKASHIC_WORKSPACE:?请先确认当前工作区并设置 AKASHIC_WORKSPACE}"
SKILL_ROOT="$AKASHIC_WORKSPACE/skills"
mkdir -p "$SKILL_ROOT"
3. 从 GitHub 仓库或本地路径安装
外部技能仓库通常有两种目录形态(兼容 Claude Code / Codex / OpenClaw 等常见 SKILL.md 仓库):
- 单技能仓库:仓库根目录下直接是
SKILL.md - 多技能集合仓库:
skills/<skill-name>/SKILL.md或<skill-name>/SKILL.md(例如https://github.com/<owner>/<repo>/tree/<branch>/skills/<skill-name>)
标准安装步骤
- 克隆到隔离临时目录(不要直接 clone 到
skills/根目录,避免残留.git或嵌套层级错误):TMP_DIR="$(mktemp -d "${TMPDIR:-/tmp}/akashic-skill.XXXXXX")" git clone --depth 1 https://github.com/<owner>/<repo>.git "$TMP_DIR/repo" - 定位
SKILL.md所在的技能目录并检查内容:- 找到目标
<skill-dir>/SKILL.md,确认 frontmatter 至少包含name和description。 - 若外部
SKILL.md带有metadata字段,注意 Akashic 解析规则:当metadata为字符串时必须能被json.loads解析为 JSON 对象(或直接写成 YAML 映射对象);若原文件使用了非 JSON 的自由文本metadata,安装后需用edit_file修正或移除该字段,否则解析会报错。 - 检查
metadata.akashic.requires(或metadata.requires)中的bins/env在本机是否满足。
- 找到目标
- 先准备完整副本,再替换目标目录。核对
<skill-name>是单个目录名,且目标在当前SKILL_ROOT内。先在同一文件系统、扫描目录外复制;复制失败时旧技能保持原样:
仅在上述命令成功后继续。检查新副本内的RECOVERY_DIR="$(mktemp -d "$AKASHIC_WORKSPACE/.skill-install.XXXXXX")" cp -R "$TMP_DIR/repo/skills/<skill-name>" "$RECOVERY_DIR/new" && test -s "$RECOVERY_DIR/new/SKILL.md".git、链接与资源路径;不要把仓库元数据或指向临时目录的链接带入安装目录。目标已存在时,将整个旧目录移到$RECOVERY_DIR/previous,保留用户改动和资源;再把$RECOVERY_DIR/new移到$SKILL_ROOT/<skill-name>。发布失败就把previous移回原处。备份不能放在skills/内,否则会被当成第二个技能扫描。 - 调用
load_skill验证后再清理本次临时 clone。验证失败时保留失败副本并恢复previous,重新加载确认旧技能可用。向用户报告恢复点;不自动删除旧技能副本。启用shell_restore时按其实际移动行为核对清理结果,只处理本次创建的临时目录。
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 · 75 lines · 118 tokens per session scan A 0f7929dc838a
skill-installer is a skill published in the GitHub repository kachofugetsu09/akashic-agent (518 stars, last pushed today), licensed MIT. It adds 118 tokens to every session and 1,692 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-11-05.
skill-installer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skill-installerkachofugetsu09/akashic-agent | Skill | 518 | today | MIT | A | 118 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |