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 instructions/thesethrose/copilot-skills/git-opsgit clone --depth 1 https://github.com/TheSethRose/Copilot-SkillsWhat 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 | $0.01811 | $0.01811 |
| Opus 5 | $0.00905 | $0.00905 |
| Sonnet 5 | $0.00362 | $0.00362 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
Copilot-Skills git-ops.instructions.md 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Operations - Automatic Context Instructions
Related Prompt: /git-ops
Related Skill: .github/copilot-skills/git-ops/SKILL.md
Triggers: git, commit, merge, rebase, push, pull, branch, checkout, stash, conflict, github, pull request, PR, force push
Context: Git Version Control Operations
When working with Git-related files or when user queries contain version control keywords, this context is automatically activated.
Core Principles
Safety First
- Always check status before destructive operations
- Create backups before force operations or history rewrites
- Verify branch before pushing or merging
- Preview changes with
--dry-runflags when available
Professional Workflow
- Atomic commits - One logical change per commit
- Descriptive messages - Use conventional commit format
- Feature branches - Never commit directly to main/master
- Pull before push - Always sync with remote first
Default Behaviors
When user mentions "commit"
- Suggest
/git-opsskill prompt - Run
git statusto show current state - Use conventional commit format:
type(scope): message - Validate commit message length and format
- Check for common mistakes (large files, secrets, debug code)
When user mentions "merge" or "rebase"
- Suggest
/git-opsskill prompt - Check current branch (prevent accidental main branch operations)
- Verify working directory is clean
- Show merge/rebase preview
- Prepare conflict resolution strategy
When user mentions "push" or "force"
- Suggest
/git-opsskill prompt with safety warnings - Load
.github/copilot-skills/git-ops/safety.mdfor force push guidelines - Verify remote branch state
- Use
--force-with-leaseinstead of--force - Confirm push target is correct
When user mentions "conflict"
- Suggest
/git-opsskill prompt - Show conflict files with
git status - Use bundled script:
.github/copilot-skills/git-ops/scripts/conflict_resolver.sh - Explain merge markers and resolution strategies
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.
- 2d ago First seen · 246 lines · 1,811 tokens per session scan A 5c6a3ee4749b
Copilot-Skills git-ops.instructions.md is an instructions file published in the GitHub repository TheSethRose/Copilot-Skills (3 stars, last pushed 8mo ago), licensed MIT. It adds 1,811 tokens to every session, about $0.0091 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 instructions, from other repositories
dotnet-skills copilot-instructions.md
Instructions for managedcode/dotnet-skills: Use AGENTS.md as the repository-wide source of truth for workflow, catalog structure, release policy, and skill maintenance rules.
copilot copilot-instructions.md
Instructions for navikt/copilot, covering copilot instructions for navikt/copilot, repository overview, nav development standards, nav principles and nav tech stack.
copilot AGENTS.md
Instructions for navikt/copilot, covering agents.md for navikt/copilot, what this repo is, efficiency rule, standard commands and conventions.
github-copilot-superpowers copilot-agent.instructions.md
Instructions for kasuken/github-copilot-superpowers, covering copilot agent instructions, 🎯 instruction hierarchy, 📋 execution order vs priority, execution order (workflow sequence) and ⛔ mandatory response template (every request).
github-copilot-superpowers subagents.instructions.md
Instructions for kasuken/github-copilot-superpowers, covering subagent instructions (ssot), terminology, agent role: orchestrator only, ⚠️ absolute rules (non-negotiable) and mcp delegation rules.
dotnet-skills GEMINI.md
Instructions for managedcode/dotnet-skills, a project described as: Installable .NET skill catalog and CLI for Codex, Claude Code, GitHub Copilot, and Gemini.