git-operations

git-operations is a skill for Claude Code, Codex from BuildrAI/Buildr. It costs 34 tokens per session (2,949 once invoked), scanned A, original, MIT.

A tool for carrying out one Git operation that has already been selected, such as fetch, rebase, commit, push, or commit and push. Git is the system that records code history and shares it with remote repositories.

In plain words
What is it for?
Use it for an explicitly scoped Git action during direct repository work or formal task delivery, with a result record showing what happened.
Why use it?
It checks the exact repository, references, files, and allowed effects before changing local files, history, or a remote branch.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it for an explicitly scoped Git action during direct repository work or formal task delivery, with a result record showing what happened.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/buildrai/buildr/git-operations
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 BuildrAI/Buildr --skill git-operations
Clone the repo
git clone --depth 1 https://github.com/BuildrAI/Buildr

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.

agentmods badge for git-operations

README.md
[![agentmods](https://agentmods.dev/badge/skills/buildrai/buildr/git-operations/github.svg)](https://agentmods.dev/skills/buildrai/buildr/git-operations)
Your own site
<a href="https://agentmods.dev/skills/buildrai/buildr/git-operations"><img src="https://agentmods.dev/badge/skills/buildrai/buildr/git-operations/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 git-operations

Your own site · 80×15
<a href="https://agentmods.dev/skills/buildrai/buildr/git-operations"><img src="https://agentmods.dev/badge/skills/buildrai/buildr/git-operations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,949 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00034 $0.02949
Opus 5.5 $0.00014 $0.01180
Sonnet 5.5 $0.00007 $0.00590
Haiku 4.5 $0.00003 $0.00295

Measured 9d ago against content hash ee6687546e49, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git-operations 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 9d 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.

projects/product/services/buildr/resources/workspace/skills/buildr/git-operations/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Operations

本 Skill 是 buildr.git-operations/v1 的默认 provider。它只帮助 Agent 安全执行 consumer 已经选定的一次 Git Operation;不讲解完整 Git 命令集,不选择交付目标或顺序,不拥有任务验证、任务结果或 workspace sync 状态。

任务工作树(Worktree)的跨库统一命名、创建和复用检查由任务工作树技能(Task Worktree Skill)承接,实际动作遵守当前有效能力绑定(Capability Binding)。本技能(Skill)核对已选操作(Operation)的真实代码库(Repository)、分支(Branch)及授权,不按名称推断任务关联或自动重命名已有对象。

能力名称使用复数 Git Operations;一次具体动作称为一个 Git Operation。

1. 先取得完整调用边界

写入前必须明确并核验:

  • 实际 repository;
  • 本次 operation;
  • 相关 source/local ref,以及远端动作适用时的 remote 与 destination ref;
  • 精确 owned paths/hunks 或已授权 commit scope;
  • 获准改变 working tree、local history 和 remote 的具体 effects。

直接用户指令、task-finish 或其他上游智能体(Agent)/consumer可以提供这些输入。用户明确要求“收尾”时,task-finish 提供的当前任务范围内常规提交、集成和普通推送授权就是明确授权;本提供者(Provider)不得仅因用户未逐项重述 Git 操作而重复询问。智能体拥有交付策略、动作、目标和顺序。同一任务已明确的写入授权,在repository、operation、ref、scope与effects未变且未被撤回时继续适用;每次写入仍重验当前事实。其他任务或范围变化不能沿用旧授权,也不得自行补选repository、ref、remote或策略。任何输入与当前事实不一致时,在零Git写入状态返回blocked。

2. 保持 operation 单一

  • fetch:只更新 consumer 明确提供的 remote/ref,不改变 working tree 或 local branch history。
  • rebase:只把 consumer 明确提供的 clean local branch rebase 到已核验 target ref,不隐含 push、merge、stash 或其他 branch/remote 选择。
  • commit:只创建或安全 amend local commit,不 push。
  • push:只发布已有 commit,不把 dirty 自动 commit。
  • commit+push:caller 依次执行一次 commit 和一次 push,保留两个独立 Result;不是原子 transaction。
  • delete-remote-ref:只删除 consumer 明确提供的 remote/ref,并以 consumer 已观察的精确远端提交为删除条件,不动其他引用。
  • workspace update:只有 Buildr Skill 等 consumer 已明确 workspace、upstream、update operation 与授权时才执行;dirty、divergence、冲突、缺失 upstream 或策略不唯一时 blocked,不自动 rebase、merge 或继续 sync。

直接 Git 收尾由智能体(Agent)选择已授权的动作,可在同一次工具调用内顺序执行。每项操作(Operation)分别核验并保留结果(Result),后一步消费已成功动作返回的真实身份;推送前新观察远端并核对完整范围。独立结果不要求独立的模型往返,批量编排不扩大授权。失败时停止相关后续动作,返回已成功部分与诊断;provider不自动stash,rebase冲突、目标歧义、已共享历史或需要force push时停止。Git Operations自身不写Task lifecycle evidence,任务登记交回原应用。

本版不预扩 checkout、reset、cherry-pick、stash、本地 branch deletion 等完整命令路由。rebase、merge、revert 或其他动作只有被 consumer 明确选为当前 operation 时才可能进入;不得作为发现分叉或失败后的自动替代策略。

Read the full file on GitHub · 122 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. 9d ago Changed · +2 lines ee6687546e49
  2. 25d ago Changed · +19 lines 54eb8243d658
  3. 1mo ago Changed a82f20aca446
  4. 1mo ago Changed 9eff12484955
  5. 1mo ago Changed · -71 tokens per session 401a5383317f
  6. 1mo ago Changed 0a7de40295d7
  7. 1mo ago Changed 3da9b8eae5a3
  8. 1mo ago Changed 8384c1b3dad5
  9. 1mo ago First seen · 101 lines · 105 tokens per session scan A 4a5a4b1c4289

Subscribe to this mod's changes

git-operations is a skill published in the GitHub repository BuildrAI/Buildr (28 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 2,949 once invoked, about $0.0001 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 2026-08-30.