ZCF is a command-line setup tool for configuring Claude Code and Codex with agents, instructions, skills, hooks, commands, and settings. It is for developers who want to install and personalize these coding-agent workflows through an interactive setup.
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 UfoMiao/zcf --skill git-clean-branchesgit clone --depth 1 https://github.com/UfoMiao/zcfWrote 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/ufomiao/zcf/git-clean-branches)<a href="https://agentmods.dev/skills/ufomiao/zcf/git-clean-branches"><img src="https://agentmods.dev/badge/skills/ufomiao/zcf/git-clean-branches/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.
<a href="https://agentmods.dev/skills/ufomiao/zcf/git-clean-branches"><img src="https://agentmods.dev/badge/skills/ufomiao/zcf/git-clean-branches.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 61 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.
- medium Excessive Agency · line 24 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 45 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00027 | $0.01057 |
| Opus 5.5 | $0.00011 | $0.00423 |
| Sonnet 5.5 | $0.00005 | $0.00211 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
git-clean-branches 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 2mo 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Command: Clean Branches
This command safely identifies and cleans up merged or stale Git branches.
Runs in read-only preview (--dry-run) mode by default, requiring explicit instructions to perform deletions.
Usage
# [Safest] Preview branches to be cleaned without executing any deletions
/git-cleanBranches --dry-run
# Clean local branches merged to main and inactive for over 90 days (requires individual confirmation)
/git-cleanBranches --stale 90
# Clean local and remote branches merged to release/v2.1 (auto-confirm)
/git-cleanBranches --base release/v2.1 --remote --yes
# [Dangerous] Force delete an unmerged local branch
/git-cleanBranches --force outdated-feature
Options
--base <branch>: Specify the base branch for cleanup (defaults to repository'smain/master).--stale <days>: Clean branches with no commits for specified days (disabled by default).--remote: Also clean remote merged/stale branches.--dry-run: Default behavior. Only list branches to be deleted without executing any operations.--yes: Skip individual confirmations and delete all identified branches directly (suitable for CI/CD).--force: Use-Dto force delete local branches (even if unmerged).
What This Command Does
-
Configuration and Safety Checks
- Update Information: Automatically executes
git fetch --all --pruneto ensure branch status is current. - Read Protected Branches: Reads the list of branches that should not be cleaned from Git config (see "Configuration" below).
- Determine Base: Uses
--baseparameter or auto-detectedmain/masteras comparison baseline.
- Update Information: Automatically executes
-
Analysis and Identification (Find)
- Merged Branches: Find local (and remote if
--remoteis added) branches fully merged to--base. - Stale Branches: If
--stale <days>is specified, find branches with last commit N days ago. - Exclude Protected Branches: Remove all configured protected branches from cleanup list.
- Merged Branches: Find local (and remote if
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.
- 2mo ago First seen · 100 lines · 27 tokens per session scan A 1027e768d74a
git-clean-branches is a skill published in the GitHub repository UfoMiao/zcf (6,070 stars, last pushed 17d ago), licensed MIT. It adds 27 tokens to every session and 1,057 once invoked, about $0.0001 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.
git-clean-branches compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| git-clean-branchesUfoMiao/zcf | Skill | 6.1k | 17d ago | MIT | A | 27 | Claude Code |
| cli-forge-githubDestynova2/cli-code-skills | Skill | 5 | 2mo ago | MIT | A | 165 | Claude Code |
| cli-git-conventionalDestynova2/cli-code-skills | Skill | 5 | 2mo ago | MIT | A | 128 | Claude Code |
| rea-changelog-updatemorluto/rea | Skill | 461k | today | MIT | A | 33 | Claude Code |
| repo-hygieneQwenLM/qwen-code | Skill | 30k | today | Apache-2.0 | A | 48 | Claude Code, Codex |
| gh-skillcli/cli | Skill | 47k | yesterday | MIT | A | 41 | Claude Code, Codex |
| cw-gatesHmbown/Codewhale | Skill | 41k | 1mo ago | MIT | A | 48 | Claude Code, Codex |