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/0x0w1/jig/jig-github-releasenpx skills add 0x0w1/jig --skill jig-github-releasegit clone --depth 1 https://github.com/0x0w1/jigWrote 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/0x0w1/jig/jig-github-release)<a href="https://agentmods.dev/skills/0x0w1/jig/jig-github-release"><img src="https://agentmods.dev/badge/skills/0x0w1/jig/jig-github-release.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 | $0.00071 | $0.03342 |
| Opus 5 | $0.00036 | $0.01671 |
| Sonnet 5 | $0.00014 | $0.00668 |
| Haiku 4.5 | $0.00007 | $0.00334 |
Grade A, and why
jig-github-release 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 today.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- github-release — 97% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Release
Use this repository skill for release execution.
Release Model
- A release promotes the current
origin/developtomainwith a fast-forward push:git push origin develop:main. There is no release PR and norelease/*branch. developmust already contain every intended release change, squash-merged throughdevelop-task-flow.- The bump is graded against this project's version rubric, not against a rule inside this skill. See Version Rubric.
- The next version is computed from the latest
vX.Y.Ztag using the graded bump type. See Version Format. - The release tag and GitHub release are created from the CLI with
git tagandgh release create. - Release notes are written by the agent from the commits in
<previous tag>..<new tag>, categorized by conventional commit prefix.
GitHub Profile
Before any gh command, resolve the host from JIG_GITHUB_HOST, local jig.githubHost, then github.com, and resolve the profile from JIG_GITHUB_PROFILE, then local jig.githubProfile. If a profile is configured, read its credential with gh auth token --hostname <host> --user <profile> without printing it and run every gh command with that credential through GH_TOKEN (github.com or *.ghe.com) or GH_ENTERPRISE_TOKEN (other hosts). Verify gh api user --jq .login matches the profile. Do not use gh auth switch; fall back to the globally active account only when neither the environment nor local config selects a profile.
Version Rubric
The grading rubric is not in this skill. It is a project-owned file, so every project grades by its own axis. The version-rubric skill owns that file.
Resolve the rubric path in this order:
JIG_VERSION_RUBRICenvironment variable (session-only override).git config --local --get jig.versionRubric(repository override)..jig/versioning.md(the convention).
Apply it like this:
- Grade with the rubric's
## Decision Order: ask its questions in order and stop at the first match. That ordering is fixed; a rubric cannot change it. - Check the graded bump against the rubric's
## Grade Definitionsbefore computing the version, and quote the deciding question in the report. - Apply
## Hard Rulesafter the ordered questions. A rubric without that section has no escalation rule. - A missing optional section (
## Hard Rules,## Interface Paths,## Release Notes,## Version Format,## Pre-Release Checks) means that rule does not apply. - Rubrics written before the contract switched to English carry Korean titles, and they stay valid. Accept either spelling for every section:
## 판정 순서,## 등급 정의,## 강경 규칙,## 인터페이스 경로,## 릴리즈 노트,## 버전 형식,## 릴리즈 전 검증, and> 기준:for> Basis:. Read the file as it is; never retitle it during a release. - Read sections beyond the contract as grading context; a project may list what counts as its public interface there.
- Report the rubric path, its source, and whether it records the adopted default or a project-specific rubric.
- Never edit the rubric file from this skill.
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.
- today Changed 5b5013753d4f
- 3d ago First seen · 187 lines · 71 tokens per session scan A b7dd3d0af32e
jig-github-release is a skill published in the GitHub repository 0x0w1/jig (5 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 3,342 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
git-ship
自动化 Git 工作流一键发布助手，执行完整的「ship」流程： 基于最新 main 切新分支 → commit → 推送 → 创建 PR → squash merge → 回 main。 调用 ship 本身就是对完整流程的授权；自动推断分支名、commit message 和 PR 内容， 并主动解决 Git 冲突、测试、lint、类型检查、构建和 CI 失败，持续修复和重试， 直到改动成功合并。不要因可自行修复的失败暂停，只在认证、权限、仓库保护等 无法由当前环境解决的外部阻塞出现时请求用户介入。 仅在用户明确表达「ship」意图时触发，例如： 直接说「ship」「/ship」「git ship」 明确要求完整走完 git…
wu5-dev-flow
使用可审计的 SDD、严格 RED-GREEN-REFACTOR TDD 与安全 Git 门禁初始化、开发、修复、重构和交付 Python 项目。用于任何会修改项目源码、测试、规格、依赖或 Git 历史的任务，也用于继续跨 Session 的现有 spec/ 变更、审查代码、验证完成状态、创建提交或准备 GitHub PR。.
ascii-diagram-creator-skill
Create ASCII diagrams from workflow definitions and save them as image files (PNG, SVG, etc.).
watchfire
Operate Watchfire — the local orchestrator that runs coding agents (Claude Code, Codex, Gemini, opencode, Copilot) on tasks in sandboxed git worktrees and merges the results. Use when asked to run/queue/inspect Watchfire tasks or agents, drive the factory loop (create → run → wait → review), check why an agent is…
ship
Use when ready to ship code to remote — handles direct push to main and PR-based feature branch flows. Do NOT use for partial workflows like just committing or just pushing.
git-branch-workflow-setup-skill
Orchestrate dev-to-uat-to-main branch workflow setup during project init — detects need, prompts user via question tool, delegates to repo-ops-specialist-subagent.