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-rollbackgit 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-rollback)<a href="https://agentmods.dev/skills/ufomiao/zcf/git-rollback"><img src="https://agentmods.dev/badge/skills/ufomiao/zcf/git-rollback/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-rollback"><img src="https://agentmods.dev/badge/skills/ufomiao/zcf/git-rollback.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 54 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 56 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 Prompt Injection · line 33 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00025 | $0.00993 |
| Opus 5.5 | $0.00010 | $0.00397 |
| Sonnet 5.5 | $0.00005 | $0.00199 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
git-rollback 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Command: Git Rollback
Purpose: Safely and visually rollback a specified branch to an older version.
Defaults to read-only preview (--dry-run); actual execution requires --yes or interactive confirmation.
Usage
# Pure interactive: list branches → select branch → list recent 20 versions → select target → choose reset or revert → confirm
/git-rollback
# Specify branch, other interactive
/git-rollback --branch feature/calculator
# Specify branch and target commit, execute with hard-reset in one go (dangerous)
/git-rollback --branch main --target 1a2b3c4d --mode reset --yes
# Generate revert commit only (non-destructive rollback), preview
/git-rollback --branch release/v2.1 --target v2.0.5 --mode revert --dry-run
Options
| Option | Description |
|---|---|
--branch <branch> |
Branch to rollback; interactively selected if omitted. |
--target <rev> |
Target version (commit hash, tag, or reflog reference); interactively selects recent --depth entries if omitted. |
--mode reset|revert |
reset: Hard rollback history; revert: Generate reverse commits keeping history intact. Prompts by default. |
--depth <n> |
List recent n versions in interactive mode (default 20). |
--dry-run |
Enabled by default, only preview commands to be executed. |
--yes |
Skip all confirmations and execute directly, suitable for CI/CD scripts. |
Interactive Flow
- Sync remote →
git fetch --all --prune - List branches →
git branch -a(local + remote, filter protected branches) - Select branch → User input or parameter
- List versions →
git log --oneline -n <depth>+git tag --merged+git reflog -n <depth> - Select target → User inputs commit hash / tag
- Select mode →
resetorrevert - Final confirmation (unless
--yes) - Execute rollback
reset:git switch <branch> && git reset --hard <target>revert:git switch <branch> && git revert --no-edit <target>..HEAD
- Push suggestion → Prompt whether to
git push --force-with-lease(reset) or regulargit push(revert)
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 · 88 lines · 25 tokens per session scan A 70d00de6b14d
git-rollback is a skill published in the GitHub repository UfoMiao/zcf (6,078 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 993 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.
Other skills, from other repositories
cli-forge-github
Audit and fix GitHub repository health: rulesets vs CI alignment, branch hygiene, PR lifecycle, release automation flow, permission issues, and transient CI failures. Detects misconfigurations that cause PRs to hang, CI to fail silently, branches to accumulate, and releases to stall. Use when the user says 'PR stuck'…
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'…
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
gh-skill
Manage agent skills with gh skill. Use this skill to discover, preview, install, update, and publish Agent Skills so an agent can self-manage the skills available in its environment.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.