git-operations

git-operations is a skill for Claude Code, Codex from GoogleCloudPlatform/scion. It costs 50 tokens per session (482 once invoked), scanned A, original, Apache-2.0.

Safety guidance for using Git with Scion-managed coding agents. Git is the version-control system used to track code changes, branches, and commits.

In plain words
What is it for?
Use it when cleaning a workspace, handling files shared between agents, rebasing after deletions, or deciding which Git cleanup command is safe.
Why use it?
It reduces the risk of deleting ignored files, losing downloaded data, or creating problems when rebasing branches.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when cleaning a workspace, handling files shared between agents, rebasing after deletions, or deciding which Git cleanup command is safe.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/googlecloudplatform/scion/git-operations
About the project

Scion is a multi-agent orchestration platform that runs several isolated agents concurrently in containers, optionally giving each one its own workspace and credentials. It is used to coordinate coding and other research or operations tasks across local machines, remote virtual machines, and Kubernetes clusters. Catalogue add-ons provide workflows and controls for operating Scion.

GoogleCloudPlatform/scion · 1,900 stars · on GitHub

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 GoogleCloudPlatform/scion --skill git-operations
Clone the repo
git clone --depth 1 https://github.com/GoogleCloudPlatform/scion

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/googlecloudplatform/scion/git-operations/github.svg)](https://agentmods.dev/skills/googlecloudplatform/scion/git-operations)
Your own site
<a href="https://agentmods.dev/skills/googlecloudplatform/scion/git-operations"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/scion/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/googlecloudplatform/scion/git-operations"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/scion/git-operations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 482 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 warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 19
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 22
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 $0.00050 $0.00482
Opus 5.5 $0.00020 $0.00193
Sonnet 5.5 $0.00010 $0.00096
Haiku 4.5 $0.00005 $0.00048

Measured 1mo ago against content hash 6529354c6a9d, 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 1mo 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.

resources/platform_skills/git-operations/SKILL.md · 35 lines

What it actually says

Git Operations

General git safety rules for Scion agents. These apply regardless of workspace sharing mode — for mode-specific guidance (worktree isolation, shared-plain index hazards, clone-per-agent remotes), see the git-sandbox skill.

Working Tree Reset Safety

When cleaning a working tree, use git clean -fd, not git clean -fdx.

  • git clean -fd removes untracked files but respects .gitignore — .scion/, agent state, and ignored directories survive.
  • git clean -fdx deliberately defeats .gitignore and deletes everything not tracked by git, including .scion/, downloads/, and any local state.

The -x flag is not a stronger clean — it is a different operation. Default to -fd; use -x only with a specific reason and after verifying nothing irreplaceable is in an ignored directory.

downloads/ is an inbox, not storage. Files downloaded into your container are visible only inside it and invisible to every other agent. Move anything worth keeping to /scion-volumes/scratchpad/ (shared across all agents) promptly. A downloads/ file that has not been drained to the scratchpad is one command from gone.

Rebase After Deletion

When a PR deletes a file, a rebase will tell you about edits to that file and will not tell you about new references to it.

A concurrent edit to the deleted file raises a modify/delete conflict and halts the rebase — that case is handled, because it demands a decision. A concurrent edit that adds a reference to the deleted file from a different file produces no conflict at all: git sees two disjoint changes, reports "Successfully rebased," and leaves a dangling reference.

After rebasing a deletion, grep for the deleted name. Any inbound-reference count taken before the rebase is stale by construction.

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. 1mo ago First seen · 35 lines · 50 tokens per session scan A 6529354c6a9d

Subscribe to this mod's changes

git-operations is a skill published in the GitHub repository GoogleCloudPlatform/scion (1,900 stars, last pushed yesterday), licensed Apache-2.0. It adds 50 tokens to every session and 482 once invoked, about $0.0002 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.