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 skills add jl-cmd/claude-dev-env --skill fresh-branchgit clone --depth 1 https://github.com/jl-cmd/claude-dev-envWrote 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.
[](https://agentmods.dev/skills/jl-cmd/claude-dev-env/fresh-branch)<a href="https://agentmods.dev/skills/jl-cmd/claude-dev-env/fresh-branch"><img src="https://agentmods.dev/badge/skills/jl-cmd/claude-dev-env/fresh-branch.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00075 | $0.01653 |
| Opus 5 | $0.00037 | $0.00826 |
| Sonnet 5 | $0.00015 | $0.00331 |
| Haiku 4.5 | $0.00007 | $0.00165 |
Grade A, and why
fresh-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 7d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fresh-branch
Creates a new branch from a fresh-fetched origin/main inside an isolated git worktree under a configured isolated root. Default root is the repository's .claude/worktrees/; pass --worktree-root for an absolute alternate root (including outside the repo). Every worktree path must resolve under that root. Shared primitive: other skills invoke /fresh-branch when they need a clean branch without touching the caller's dirty tree.
Announce at start: "Creating a fresh branch from origin/main."
When this applies
- User or caller wants a new branch based on current
origin/main. - Caller needs the branch path/name as a return value for a later PR step.
Does not apply (refuse with the quoted line):
- Switch to an existing branch →
Use git switch / checkout for an existing branch; /fresh-branch only creates new ones. - Push or open a PR →
This skill only creates the branch worktree; push and PR are separate.
Checklist
- [ ] Phase 1 — confirm repo context (cwd or --repo)
- [ ] Phase 2 — resolve branch name (AskUserQuestion when needed)
- [ ] Phase 3 — execute the create script; parse JSON
- [ ] Phase 4 — report branch, worktree_path, base_commit; return to caller
Phase 1 — Repo context
Work against the repository the user has open (or the path the caller names). The script resolves the git toplevel from --repo (default .). Do not invent a different clone.
Phase 2 — Branch name (high freedom)
Branch names: lowercase, hyphen-separated, optional prefix/description.
When a topic is available: suggest 2–4 names via AskUserQuestion. Poll recent remote names for local convention:
git branch -r --sort=-committerdate
(Take a short head of that list in the shell you use; do not require Unix head.)
When no topic: ask for a name via AskUserQuestion (multiSelect: false, free-text option).
Phase 3 — Create branch (execute the script)
Execute the bundled CLI (do not reimplement with ad-hoc git checkout -b):
What ships with it
9 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.
- .claude/CLAUDE.md 14 B
- AGENTS.md 1 B
- scripts/create_fresh_branch.py 14 KB runs code
- scripts/fresh_branch_git_commands.py 8.2 KB runs code
- scripts/fresh_branch_scripts_constants/__init__.py 58 B runs code
- scripts/fresh_branch_scripts_constants/fresh_branch_cli_constants.py 2.6 KB runs code
- scripts/pytest.ini 92 B
- scripts/test_create_fresh_branch.py 33 KB runs code
- scripts/test_fresh_branch_git_commands.py 11 KB runs code
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.
- 7d ago First seen · 132 lines · 75 tokens per session scan A afa2c5e0e6a6
fresh-branch is a skill published in the GitHub repository jl-cmd/claude-dev-env (5 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 1,653 once invoked, about $0.0004 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".