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 skills/emaraschio/cursor-commands/commit-same-branchnpx skills add emaraschio/cursor-commands --skill commit-same-branchgit clone --depth 1 https://github.com/emaraschio/cursor-commandsWhat 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 | $0.00014 | $0.00277 |
| Opus 5 | $0.00007 | $0.00138 |
| Sonnet 5 | $0.00003 | $0.00055 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade A, and why
commit-same-branch 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.
What it actually says
Overview
Commit changes to the same branch with proper commit message.
Steps
-
Write commit message
- Must use the conventional commit message convention.
- Summarize changes clearly
-
Commit changes
- Use a single commit for the changes
- Commit the changes to the branch
- Push the changes to the remote repository
Commit Message Examples
feat(scope): add new feature
fix(script): resolve script error
chore(script): update script dependencies
refactor(script): standardize script error handling
test(script): add comprehensive script tests
docs(script): update script documentation
Guardrails
- Commit only when the user asks; do not commit unrequested work.
- Do not push unless asked; keep commits local until the user requests a push.
- Use the Conventional Commits convention for every message.
- Before staging, review
git status,git diff, and recentgit log; write the commit message with a HEREDOC and stay on the current branch (do not create a new branch). - Never print, stage, or commit secrets or credential files (.env, .env.*, keys); exclude them and warn instead.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 38 lines · 14 tokens per session scan A 1f14dd62c069
commit-same-branch is a skill published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 25d ago), licensed MIT. It adds 14 tokens to every session and 277 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.
Other skills, from other repositories
grok-build-supervisor
Initialize the persistent local proxy, then immediately ensure a visible Grok Build TUI for the current workspace when /grokexecute on activates, and continuously supervise that coding-agent session through a user-level Supervisor daemon as the user sends work, waits for completion, reconnects from another host task…
cursor-delegate
Delegate bounded light-to-medium implementation, limited investigation, documentation, configuration, testing, and tooling work to Cursor Bridge after the primary agent owns the direction and risk boundaries. Use when a bounded Cursor pass can save primary-agent time, reduce omissions, or run alongside non-conflicting…
grok-executor-mode
Task-local execution policy applied to ordinary user tasks only after an exact /grokexecute on; the host agent then plans, supervises, corrects, and verifies while all implementation and workspace-mutating execution goes through Grok Build Supervisor. Never activate or deactivate from ordinary requests, task text…
deep-research
Conducts multi-step deep research on any topic using iterative search, reflection, and synthesis. Use when the user asks to research, investigate, survey, compare, analyze, deep-dive, or explore a topic in depth. Covers web research, codebase analysis, documentation review, mixed-source investigation, and M3…
incident-triage-harness
Production-style incident triage workflow for logs, metrics, code, safe mitigations, and M3 multimodal visual evidence (screenshots, screen recordings). Use when debugging alerts, regressions, outages, or suspicious runtime behavior.
evaluate-dependency
Use when adding or evaluating a project dependency in any language, phrases like "should I use X library", "evaluate ", "what library for Y", or when reviewing a PR that touches a manifest (go.mod, package.json, requirements.txt, pyproject.toml, Cargo.toml, Gemfile, mix.exs, composer.json). Also use when comparing…