What is verify-akashic-plugin?

A plugin acceptance skill that commits a plugin, installs it into the running application, checks its status, and uses it once to confirm whether it works.

Use it after writing or changing an Akashic plugin when you need to verify the installed commit and report only what the checks prove.

Installation, activation, and actual operation are separate checks; this workflow gathers evidence for each instead of treating installation as proof.

verify-akashic-plugin — Skill by kachofugetsu09/akashic-agent

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.

Any agent

npx skills add kachofugetsu09/akashic-agent --skill verify-akashic-plugin

Clone the repo

git clone --depth 1 https://github.com/kachofugetsu09/akashic-agent

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kachofugetsu09/akashic-agent/verify-akashic-plugin/github.svg)](https://agentmods.dev/skills/kachofugetsu09/akashic-agent/verify-akashic-plugin)

Your own site

<a href="https://agentmods.dev/skills/kachofugetsu09/akashic-agent/verify-akashic-plugin"><img src="https://agentmods.dev/badge/skills/kachofugetsu09/akashic-agent/verify-akashic-plugin/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kachofugetsu09/akashic-agent/verify-akashic-plugin"><img src="https://agentmods.dev/badge/skills/kachofugetsu09/akashic-agent/verify-akashic-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,554 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00053	$0.01554
Opus 5.5	$0.00021	$0.00622
Sonnet 5.5	$0.00011	$0.00311
Haiku 4.5	$0.00005	$0.00155

Measured 2d ago against content hash 8f0060b0d8fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-akashic-plugin scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/shoot_page.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| WebUI | 从当前实例入口或已确认的 Web 配置取得浏览器可访问的 URL（不是 Gateway RPC 端口）。读取该 URL 的 `/api/chat/web-ui/bootstrap`，检查 `modules[].pluginId` 包含本插件，只能证明目录已发布。再跑下面的截图脚本；退出码 2 表示缺少 Playwright 或浏览器，写明"界面未亲眼验证"，不要用 curl 扒前端资源代替 |

skills/verify-akashic-plugin/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

安装并验收插件

已安装、已激活、能用是三件不同的事，每一层都要单独取证。汇报只写拿到证据的那一层。

一轮最多约 40 次模型输出。验收控制在 10 次以内；接近上限时先停下汇报已有证据，再说明还缺什么，不能因为步数用完而没有汇报。

1. 提交

cd "$AKASHIC_WORKSPACE/plugin-src/<name>" && git add -A && git commit -m "<说明>" && git rev-parse HEAD

记下完整 commit。没提交的改动不会被安装。

2. 安装

本次可见工具里有 plugin_install 就用它：source 填源码绝对路径，marketplace 填 local，ref 填完整 commit。

没有这个工具时用当前实例自带的命令行；后续查状态和新会话验收也使用同一入口。先根据执行环境确定命令前缀，后文记作 <当前CLI>：

Host Bridge 宿主有 $AKASHIC_RUNTIME_CLI：使用 "$AKASHIC_RUNTIME_CLI"，配置与 workspace 取 $AKASHIC_CONFIG、$AKASHIC_WORKSPACE。这个入口已绑定对应 release 的解释器和源码，不需要查找容器内 main.py。
本地开发实例没有该变量：从下面的真实进程中取得 python、config、workspace，使用 <python> "$AKASHIC_CORE_ROOT/main.py"。变量或进程缺席时明确报告入口未定位，不拼出 /main.py 或另起 Runtime。

ps -eo args= | grep -F "$AKASHIC_CORE_ROOT/main.py --config" | grep -v grep | head -1

安装命令（<config>、<workspace> 替换为上面取得的路径；子命令必须在配置参数之前）：

<当前CLI> plugin-install \
  --source "$AKASHIC_WORKSPACE/plugin-src/<name>" --marketplace local --ref <完整commit> \
  --config <config> --workspace <workspace>

不要另起一个 Akashic 进程，不要猜 python 路径。记下返回的 update_id 和 plugin_id（形如 <name>@local）。

3. 核对状态

<当前CLI> plugin-status <update_id> --config <config> --workspace <workspace>

state 为 active，且 active_input_ref 等于本次的 input_ref：本次输入已激活。
accepted：已接纳还没激活，间隔几秒再查，最多十次。
failed：读 error，改源码后回到第 1 步。不要反复重装同一个 commit。
restart_required：输入已选择但需重启，不能报告已生效；按已有重启授权处理，再核对同一输入。unknown：保留回执并报告尚未确认，不当成成功。

4. 实际用一次

激活只说明代码加载了，还要按插件类型取能力证据。

当前这一轮的工具和 Skill 目录在安装前就固定了，新能力在本轮看不到（load_tools 会报"不属于当前获授工具目录"）。工具和 Skill 用一个新会话验：

<当前CLI> exec --new --final-only \
  "只做一件事：调用 <工具名>，参数 <...>，把工具返回的原始结果原样贴出来，不要自己算。" \
  --config <config> --workspace <workspace> 2>&1

它新建一个程序化会话（不写记忆），等那一轮结束后只打印最终回复；失败时退出码为 1，reason 在输出里。

插件类型	怎么验
工具	用上面的 `exec`：工具组非 `always_on` 时让新会话先 `load_tools` 传插件 ID 再调用；贴出原始返回
Skill	用上面的 `exec` 让新会话 `load_skill` 并复述要点，核对来源是本插件
WebUI	从当前实例入口或已确认的 Web 配置取得浏览器可访问的 URL（不是 Gateway RPC 端口）。读取该 URL 的 `/api/chat/web-ui/bootstrap`，检查 `modules[].pluginId` 包含本插件，只能证明目录已发布。再跑下面的截图脚本；退出码 2 表示缺少 Playwright 或浏览器，写明"界面未亲眼验证"，不要用 curl 扒前端资源代替
上下文材料、后台任务	触发一次对应场景，用它产生的真实结果作证据

Read the full file on GitHub · 101 lines

Files

What ships with it

1 file 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.

scripts/shoot_page.py 6.1 KB runs code

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.

2d ago First seen · 101 lines · 53 tokens per session scan A 8f0060b0d8fd

Subscribe to this mod's changes

verify-akashic-plugin is a skill published in the GitHub repository kachofugetsu09/akashic-agent (511 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 1,554 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-14.

Commits Git and workflow Testing

github-copilot-upgrader

Use this to update the Github Copilot CLI/SDK.

microsoft/vscode · 18 tokens

workflow-patterns

Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.

wshobson/agents · 35 tokens

meta-pre-commit-quality-gate

Run three quality gates (ruff + mypy + pytest) in parallel over the staged diff, then arbitrate a single BLOCK/APPROVE verdict. Use before committing changes locally when you want a comprehensive pre-commit gate beyond per-file linting — exactly the same gate set CI enforces.

opensquilla/opensquilla · 68 tokens

verify-akashic-plugin