git

A governed Git platform management skill. Git is a system for tracking code changes, while Git hosting platforms store repositories and support collaboration.

In plain words
What is it for?
It helps authenticate and configure Git platforms, create, clone, or delete repositories, and manage related webhooks and integrations.
Why use it?
It gives agents one controlled approach for working with GitHub, GitLab, Bitbucket, and Azure DevOps. Human approval and credential controls reduce the risk of unwanted repository changes.

Skill for Claude CodeCodex

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/layer1labs/specsmith/git
Any agent
npx skills add layer1labs/specsmith --skill git
Clone the repo
git clone --depth 1 https://github.com/layer1labs/specsmith

Made for: Claude Code, Codex.

Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 742 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 $0.00012 $0.00742
Opus 5 $0.00006 $0.00371
Sonnet 5 $0.00002 $0.00148
Haiku 4.5 $0.00001 $0.00074

Measured yesterday against content hash a0b234648b5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git 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 yesterday.

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.

.agents/skills/git/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Platform Management

This skill enables specsmith projects to manage Git repositories across multiple platforms (GitHub, GitLab, Bitbucket, etc.) while maintaining governance compliance across Windows, Linux, and Mac platforms.

Requirements Covered

  • REQ-079: Git Platform Agnostic Management
  • REQ-080: GitHub Platform Management
  • REQ-081: GitLab Platform Management
  • REQ-082: Bitbucket Platform Management
  • REQ-083: Azure DevOps Platform Management
  • REQ-084: Git Platform Authentication Management
  • REQ-085: Git Platform Configuration Management
  • REQ-086: Git Platform Repository Creation
  • REQ-087: Git Platform Repository Deletion
  • REQ-088: Git Platform Repository Cloning

Integration Capabilities

Platform Features

  • Cross-platform Git repository management for GitHub, GitLab, Bitbucket, and Azure DevOps
  • Platform-specific authentication and credential management
  • Repository creation, deletion, and cloning
  • Configuration management for multiple Git platforms
  • Webhook and integration management

Governance Requirements

  • Human approval required for all Git platform operations
  • Configuration management with governance controls
  • Security best practices enforcement for Git operations
  • Audit logging of all Git platform activities

Platform-Specific Considerations

Windows

  • Path handling with Windows-specific conventions
  • Git client integration with Windows-specific tools
  • Windows-specific credential storage and management
  • File system permissions for repository access

Linux

  • POSIX-compliant path handling
  • Git client integration with standard Linux tools
  • Package manager integration for Git tools
  • System service management for Git operations

macOS

  • Darwin-specific path handling
  • macOS application integration for Git tools
  • Homebrew and MacPorts package management
  • System preferences and security frameworks

Usage Examples

# Initialize Git management
specsmith skill install git

# Configure Git platform settings
specsmith git configure --platform github --token-file ~/.github_token

# Create a new repository
specsmith git repo create --platform github --name my-project --description "My new project"

# Clone a repository
specsmith git repo clone --platform github --url https://github.com/user/repo.git

# Manage authentication
specsmith git auth setup --platform github --token mytoken123

# List repositories
specsmith git repo list --platform github

Read the full file on GitHub · 116 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. yesterday First seen · 116 lines · 12 tokens per session scan A a0b234648b5b

Subscribe to this mod's changes

git is a skill published in the GitHub repository layer1labs/specsmith (7 stars, last pushed 29d ago), licensed MIT. It adds 12 tokens to every session and 742 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

accessibility-audit

Unified accessibility audit - axe-core WCAG 2.2 scan, APCA contrast measurement, static a11y checks (aria-label, tabindex, form labels, focus visibility, onClick on non-interactive). Static and live modes.

marcoguillermaz/Tierward · 53 tokens

arch-audit

Audit Claude Code architecture files against Anthropic docs and release notes, and verify internal ecosystem consistency. Run on demand to maintain compliance, catch new features, and keep the context system clean.

marcoguillermaz/Tierward · 41 tokens

pr-review

Autonomous local code review. Reviews either an open PR's diff (via gh) or the local working diff against a base branch (--local, auto-selected when no PR exists yet), spawns a dedicated review subagent with universal + stack-specific severity criteria, posts the review as a comment on the PR (audit trail; skipped in…

marcoguillermaz/Tierward · 167 tokens

security-audit

Security audit: auth/authz on API routes, input validation, row-level access control (RLS in Postgres, ORM scopes or app-level guards elsewhere), response shape review, secret exposure, HTTP headers. Native mode checks entitlements and Keychain. MCP-aware (v1.20+): when mcp-nvd server is wired, Step 3c queries live…

marcoguillermaz/Tierward · 109 tokens

skill-db

Database audit: schema quality, index coverage, row-level access-control completeness, FK cascades, query patterns. Runs live SQL verification (PostgreSQL instance in PATTERNS.md; other engines verify the equivalent guard). Migration file safety → /migration-audit.

marcoguillermaz/Tierward · 56 tokens

skill-dev

Code quality audit: detect cross-module coupling, N+1 queries, dead exports, antipatterns, over-large components. Cross-checks against refactoring backlog.

marcoguillermaz/Tierward · 36 tokens