t-push

t-push is a skill for Claude Code, Codex from timzaak/web-dev-skills. It costs 31 tokens per session (1,094 once invoked), scanned A, original, Apache-2.0.

A controlled Git workflow that checks changed areas with local CI, then creates a commit and pushes it to the remote repository. CI means automated checks run against the code before it is saved and shared.

In plain words
What is it for?
Use it to inspect changes, clean up disallowed comments, run affected backend, frontend, or demo checks, create a commit with an AI-written message, and push after all checks pass.
Why use it?
It reduces the risk of committing code that fails the checks and keeps the commit message tied to the actual diff. It also reuses successful checks during the same push attempt when the relevant code has not changed.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the t-tools plugin — 27 skills, 31 agents shipped together

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.

agentmods
npx agentmods add skills/timzaak/web-dev-skills/t-push
Any agent
npx skills add timzaak/web-dev-skills --skill t-push
Clone the repo
git clone --depth 1 https://github.com/timzaak/web-dev-skills

Made for: Claude Code, Codex.

Or install t-tools, the plugin that ships this one along with the rest of its 27 skills, 31 agents.

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 t-push

README.md
[![agentmods](https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-push.svg)](https://agentmods.dev/skills/timzaak/web-dev-skills/t-push)
Your own site
<a href="https://agentmods.dev/skills/timzaak/web-dev-skills/t-push"><img src="https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-push.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,094 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.01094
Opus 5 $0.00015 $0.00547
Sonnet 5 $0.00006 $0.00219
Haiku 4.5 $0.00003 $0.00109

Measured 4d ago against content hash 07ca910929d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

t-push 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 4d 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.

skills/t-push/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Push with Local CI

运行时边界统一参考:${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md

Fixed Flow

先由 AI 读取 git status --short 和必要的 git diff,识别本次变更涉及的源码文件。

在生成 commit message 和调用脚本前,AI 必须清理本次变更源码文件中的违规注释:低价值注释定义、临时工作流文档(.ai/design.ai/task)引用禁令和必须保留的注释类型均以 ${CLAUDE_PLUGIN_ROOT}/protocols/code-comment-contract.md 为准。清理范围只限本次变更文件,不做全仓历史清理。

清理后重新查看必要的 git diff,确认 diff 中剩余注释有实际信息增量,再总结本次变更并生成简洁 commit message。commit message 必须来自 AI 对清理后实际变更的总结,不能由脚本根据目录名自动猜测。

然后为本次 /t-push 执行生成一个新的 session id(例如 YYYYMMDD-HHMMSS 或短 UUID)。同一次执行中,如果 CI 失败、AI 修复后需要重跑脚本,必须复用同一个 session id;新的 /t-push 执行必须生成新的 session id,避免被上一次执行的缓存影响。

使用脚本完成验证、提交和推送:

uv run ${CLAUDE_PLUGIN_ROOT}/scripts/push.py --ci-session "<本次 t-push session id>" --message "<AI 生成的 commit message>"

脚本负责:

  • 检查 git status --short,无变更时停止。
  • 读取 tracked、staged、unstaged 和 untracked 文件,检测 backend、frontend、demo 变更范围。
  • 为受影响区域并发运行本地 CI;同一区域内部保持顺序执行。
  • 记录该 session 内每个区域通过 CI 时的 diff 指纹;同一次 push 流程中重跑脚本时,已通过且 diff 未变化的区域直接跳过,避免例如 backend 通过后因为修复 frontend 又重复跑 backend。新的 /t-push 执行必须使用新的 session,不复用上次结果。
  • 使用 AI 传入的 --message 作为 commit message;执行提交时没有 --message 则停止。
  • CI 全部通过后执行 git add -Agit commitgit push

CI Rules

  • Backend 变更:依次执行 cargo clippy --fix --allow-dirty --allow-staged --all-targets --all-features -- -D warningscargo fmt --all,再执行一次不带 --fixcargo clippy --all-targets --all-features -- -D warnings 作为最终校验(--fix 遇到无法自动修复的 denied lint 时仍会以 0 退出,仅靠 --fix 无法拦截,需此步骤才能真正强制 -D warnings)。若该校验报错,AI 应根据错误信息修复代码后重新运行脚本,直到通过。
  • Frontend 变更:执行 npm run lintnpm run format:checknpm run type-check;其中 format:check 不存在时跳过。
  • Demo 变更:执行 npm run lintnpm run type-check
  • 无 backend/frontend/demo 变更时跳过本地 CI,直接进入 commit/push。

Script Commands

uv run ${CLAUDE_PLUGIN_ROOT}/scripts/push.py --ci-session "<session>" --message "<message>"
uv run ${CLAUDE_PLUGIN_ROOT}/scripts/push.py --ci-session "<session>" --message "<message>" --force-checks

Read the full file on GitHub · 66 lines

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. 4d ago First seen · 66 lines · 31 tokens per session scan A 07ca910929d3

Subscribe to this mod's changes

t-push is a skill published in the GitHub repository timzaak/web-dev-skills (69 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 1,094 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

chinese-documentation

中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.

jnMetaCode/superpowers-zh · 62 tokens

chinese-git-workflow

国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。.

jnMetaCode/superpowers-zh · 69 tokens

chinese-code-review

中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。.

jnMetaCode/superpowers-zh · 62 tokens

chinese-commit-conventions

中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用,不要根据上下文自动触发。.

jnMetaCode/superpowers-zh · 65 tokens

systematic-debugging

Skill "systematic-debugging" from jnMetaCode/superpowers-zh, covering 系统化调试, 概述, 铁律, 何时使用 and 四个阶段.

jnMetaCode/superpowers-zh · 24 tokens

dispatching-parallel-agents

当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用.

jnMetaCode/superpowers-zh · 30 tokens