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-commitgit 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-commit)<a href="https://agentmods.dev/skills/ufomiao/zcf/git-commit"><img src="https://agentmods.dev/badge/skills/ufomiao/zcf/git-commit/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-commit"><img src="https://agentmods.dev/badge/skills/ufomiao/zcf/git-commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 15 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.
- high Tool Misuse · line 77 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.
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 | $0.00041 | $0.02180 |
| Opus 5.5 | $0.00016 | $0.00872 |
| Sonnet 5.5 | $0.00008 | $0.00436 |
| Haiku 4.5 | $0.00004 | $0.00218 |
Grade A, and why
git-commit 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 1mo 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Command: Commit (Git-only)
This command works without any package manager/build tools, using only Git to:
- Read changes (staged/unstaged)
- Determine if changes should be split into multiple commits
- Generate Conventional Commits style messages with optional emoji for each commit
- Execute
git addandgit commitas needed (runs local Git hooks by default; use--no-verifyto skip)
Usage
/git-commit
/git-commit --no-verify
/git-commit --emoji
/git-commit --all --signoff
/git-commit --amend
/git-commit --scope ui --type feat --emoji
Options
--no-verify: Skip local Git hooks (pre-commit/commit-msgetc.).--all: When staging area is empty, automaticallygit add -Ato include all changes in the commit.--amend: Amend the last commit without creating a new one (preserves author and timestamp unless local Git config specifies otherwise).--signoff: AddSigned-off-byline (use when following DCO process).--emoji: Include emoji prefix in commit message (omit for plain text).--scope <scope>: Specify commit scope (e.g.,ui,docs,api), written to message header.--type <type>: Force commit type (e.g.,feat,fix,docs), overrides automatic detection.
Note: If the framework doesn't support interactive confirmation, enable
confirm: truein front-matter to avoid mistakes.
What This Command Does
-
Repository/Branch Validation
- Check if in a Git repository using
git rev-parse --is-inside-work-tree. - Read current branch/HEAD status; if in rebase/merge conflict state, prompt to resolve conflicts first.
- Check if in a Git repository using
-
Change Detection
- Get staged and unstaged changes using
git status --porcelainandgit diff. - If staged files = 0:
- If
--allis passed → Executegit add -A. - Otherwise prompt choice: continue analyzing unstaged changes for suggestions, or cancel to manually group staging.
- If
- Get staged and unstaged changes using
-
Split Suggestions (Split Heuristics)
- Cluster by concerns, file modes, change types (e.g., source code vs docs/tests; different directories/packages; additions vs deletions).
- If multiple independent changesets or large diff detected (e.g., > 300 lines / across multiple top-level directories), suggest splitting commits with pathspecs for each group (for subsequent
git add <paths>).
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.
- 1mo ago First seen · 200 lines · 41 tokens per session scan A 08a309da411e
git-commit is a skill published in the GitHub repository UfoMiao/zcf (6,078 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 2,180 once invoked, about $0.0002 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.
Other skills, from other repositories
cli-git-conventional
Enforce Conventional Commits v1.0.0, SemVer 2.0.0, branch naming, commit guard, full-directory AI marker audits, and human ghostwriter style on all git/jj operations. Zero AI markers. Use on 'commit', 'branch', 'tag', 'release', 'changelog', 'semver', 'bump version', 'next version', 'CHANGELOG.md', 'audit markers'…
cw-land
Use when turning verified Codewhale work into commits, branches, or a merge: choosing direct-main vs. worktree vs. integration branch, preserving contributor credit, and honoring the gate artifact before merging.
git-master
Handles git work: atomic commits, rebase, squash, blame, bisect, reflog, and history questions. Use whenever a task needs a commit or a git-history investigation; skip for ordinary code edits.
atmos-git
Atmos Git and GitOps: git.repositories, clone/pull/status/diff/commit/push/clean, local Git hook shims and hook env vars, signed commits, managed workdirs, fork-PR trust gate (clone gate and posting gate), and auth via identities or github/sts.
commit-pr
Mandatory Codex/Copilot publication adapter for opencode-swarm. Use for every GitHub issue assignment that results in code changes, commits, pushes, draft PRs, PR body edits, PR readying, release notes, or CI closeout. Must be loaded before git push, gh pr create, gh pr edit, or gh pr ready. Routes to the single…
conventional-commit
Conventional Commit - Generate Conventional Commits 1.0.0 compliant messages. MANDATORY for all git commits. Invoke when user says 'commit', 'commit this', or asks to commit code.