soia-meta-skill-release

soia-meta-skill-release is a skill for Claude Code, Codex from soia-team/soia-open-skills. It costs 43 tokens per session (6,168 once invoked), scanned C, original, MIT.

A release and installation tool for AI skills after their changes have been merged into the main code branch. It updates local installations, links skills to supported AI tools, and checks versions and lock files.

In plain words
What is it for?
Use it to complete a skill release, update installed skills, remove old names, synchronize Codex and Claude Code links, install WorkBuddy experts, or test a development snapshot.
Why use it?
It reduces mistakes when skills are renamed, removed, or installed in several places. Its checks help reveal leftover old copies or missing installations.

Skill for Claude CodeCodex

Written for Claude Code and Codex: Claude Code plugin machinery, but also agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/generate_marketplaces.py --help >/dev/null # 元仓 checkout 内.

Part of the soia-meta plugin — 5 skills, 1 agent shipped together

Good fit Use it to complete a skill release, update installed skills, remove old names, synchronize Codex and Claude Code links, install WorkBuddy experts, or test a development snapshot.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/soia-team/soia-open-skills
agentmods
npx agentmods add skills/soia-team/soia-open-skills/soia-meta-skill-release

Made for: Claude Code, Codex.

Or install soia-meta, the plugin that ships this one along with the rest of its 5 skills, 1 agent.

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.

agentmods badge for soia-meta-skill-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/soia-team/soia-open-skills/soia-meta-skill-release/github.svg)](https://agentmods.dev/skills/soia-team/soia-open-skills/soia-meta-skill-release)
Your own site
<a href="https://agentmods.dev/skills/soia-team/soia-open-skills/soia-meta-skill-release"><img src="https://agentmods.dev/badge/skills/soia-team/soia-open-skills/soia-meta-skill-release/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.

agentmods 80×15 button for soia-meta-skill-release

Your own site · 80×15
<a href="https://agentmods.dev/skills/soia-team/soia-open-skills/soia-meta-skill-release"><img src="https://agentmods.dev/badge/skills/soia-team/soia-open-skills/soia-meta-skill-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,168 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.06168
Opus 5 $0.00022 $0.03084
Sonnet 5 $0.00009 $0.01234
Haiku 4.5 $0.00004 $0.00617

Measured 3d ago against content hash 0667f8e90703, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

soia-meta-skill-release scanned grade C 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 3d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/formal_release.py, scripts/generate_release_notes.py, scripts/install_workbuddy_experts.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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/.codex/.tmp/marketplaces/soia
skills/soia-meta-skill-release/SKILL.md · 424 lines

How it starts

The opening of the file, as written. The whole thing — 424 lines — stays where its author put it; the contents beside it link to each section on GitHub.

soia-meta-skill-release

完成正式远端发版与市场 pin 收尾;默认只发布,不修改本机。客户明确选择项目/全局、Agent 与 skill/domain/all 后,才把安装交给 sync owner。

客户可读说明

这个技能可以做什么

客户想要 技能会做 客户能看到
发布 merge 后的一个或多个技能 远端正式版与市场 pin 收尾 发布回执与客户端更新指引
发布后按客户选择安装 转交 sync owner 的明确计划 project/global、Agent、粒度与 dry-run

客户如何使用

正式远端发版使用本文后半的 formal_release.py;下列 release_skills.py 只负责发布后的本机收口选择。先提供仓库、技能名单和可选旧名:

python3 skills/soia-meta-skill-release/scripts/release_skills.py \
  --repo <owner/name> \
  --skills <skill-a,skill-b> \
  --removed <legacy-skill> \
  --dry-run

复核 dry-run 后,移除 --dry-run 执行。默认 remote-only,不选择任何 Agent;要安装时必须明确 scope、Agent、skill/domain/all 与目标。版本核对按以下顺序解析本地 checkout:

  1. --repo-dir <repo-path> 显式路径;
  2. 当前进程的 SOIA_SKILL_REPOS_ROOT/<repo-name>
  3. 私有 YAML:--configSOIA_META_SKILL_RELEASE_CONFIG_FILE~/.config/soia-skills/soia-meta-skill-release/config.yml 中的 env.SOIA_SKILL_REPOS_ROOT
  4. v1 私有配置目录只读回退(会向 stderr 输出建议的 mv 迁移命令);
  5. 旧版维护者本地目录约定,仅作弃用中的向后兼容回退。

仓库内部仍须采用 skills/<skill-name>/SKILL.md 布局。对未来新增仓库,只要 --repo 提供对应的任意 <owner>/<repo-name>,无需修改脚本。

依赖与安装

claude plugin marketplace add soia-team/soia-open-skills
claude plugin install soia-meta@soia

需要本机安装时,先让客户明确 project/global、Agent 与 skill/domain/all;默认只发布,不生成安装命令。

npx skills add soia-team/soia-open-skills -a <explicit-agent> -s soia-meta-skill-release -y

客户明确选择 WorkBuddy 时,先按本文“WorkBuddy 专家”段运行专用脚本的 dry-run;当前只支持用户级专家目录,不把它冒充项目级安装。

依赖 类型 用途 缺失时怎么处理
npx skills 强依赖 安装、移除、更新并维护 lock 停止并报告失败步骤
soia-meta-sync-skills 定向安装时依赖 接收已确认的 scope、Agent 与粒度并执行同步 只发布不受影响;选择安装时先补齐该技能
Python 3 强依赖 执行发布脚本 安装 Python 3 后重试
PyYAML 可选依赖 读取私有 config.yml --repo-dir 或使用当前进程环境变量

私密信息与中间数据

按本仓 DATA_STORAGE_SPEC.md,本技能只读写各 AI 技能安装目录及 ~/.agents/.skill-lock.json;可选读取仅含本地 checkout 根目录的私有 v2 config.yml。复制 路径配置模板 后再填写;不要为了这一个设置修改 .zprofile,也不读取或保存凭据、缓存或中间文件。终端回执只显示技能名、版本、链接状态和失败步骤。

Read the full file on GitHub · 424 lines

Files

What ships with it

7 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.

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.

  1. 3d ago Changed · -1 lines 0667f8e90703
  2. 7d ago Changed · -7 lines · -41 tokens per session 2c3c106dbf7b
  3. 12d ago First seen · 432 lines · 84 tokens per session scan C a428d78638dc

Subscribe to this mod's changes

soia-meta-skill-release is a skill published in the GitHub repository soia-team/soia-open-skills (5 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 6,168 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

hyalo-changelog

Maintain Keep a Changelog files with Hyalo's changelog profile and add/release commands.

ractive/hyalo · 24 tokens

publish-pr

Use in /implement at the draft→ready boundary to squash the branch's review-iteration commits into one (non-interactive soft-reset + recommit + force-with-lease) and mark the draft PR ready. Takes the commit message as input (sourced from the plan-file before cleanup). GitHub-specific (gh) behind a host-neutral…

ethanaubuchon/dossier-tradecraft · 74 tokens

release-slice

Open-source one slice of a private system: take a component, sanitize it, run a leak-scan as a hard gate, publish to GitHub, then changelog, roadmap and tag on cadence, then the content wave. Publishing without passing the leak-scan is forbidden. Triggers: "/release-slice ", "ship the next slice".

tonydzi/second-brain-starter-kit · 76 tokens

release-rollback

A release and rollback checklist for code or scripts, covering readiness checks, release decisions, and recovery after an incident.

dzhokhov/markdown-agent-vault-ru · 101 tokens

carpeos-release

Cut a CarpeOS public release with consistent SemVer, CHANGELOG, git tags, GitHub Releases, and npm publish for @innocarpe/carpeos. Use when the user asks to release, bump version, publish to npm, create a git tag, make a GitHub release, ship @innocarpe/carpeos, run scripts/release.mjs, or keep Claude Code / Codex CLI…

innocarpe/CarpeOS · 107 tokens

retrospect

Run a structured retrospective on a shipped commit range, release, deployment, PR, commit, or session. Per-fix validation enforcement, active evidence-sourcing pass (autonomous lookups + targeted user-asks for anything that could become objective), simpler-alternative discipline, re-diagnosis, action verdicts, and a…

mikeprasad/aria-knowledge · 158 tokens