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.
Borrowing it
Nothing to install: this file belongs to UfoMiao/zcf. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/UfoMiao/zcf/main/.claude/skills/zcf-update-docs/SKILL.mdgit 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/zcf-update-docs)<a href="https://agentmods.dev/skills/ufomiao/zcf/zcf-update-docs"><img src="https://agentmods.dev/badge/skills/ufomiao/zcf/zcf-update-docs/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/zcf-update-docs"><img src="https://agentmods.dev/badge/skills/ufomiao/zcf/zcf-update-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 420 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 | $0.00034 | $0.00758 |
| Opus 5.5 | $0.00014 | $0.00303 |
| Sonnet 5.5 | $0.00007 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
zcf-update-docs 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ZCF Update Docs
Find user-visible changes since the last tag and update the documentation that describes them.
Usage: /zcf-update-docs [--check-only]. With --check-only, report what is out of date and change nothing. Arguments: $ARGUMENTS
Steps
- Scope. Last tag:
git describe --tags --abbrev=0. List changed files withgit diff --name-only <tag>..HEADand read the diffs of the source files that the map below covers. Ignore test-only and internal refactor changes that do not alter behavior. - Map code to pages. For each user-visible change, open the matching page in
docs/en/guide/and compare it with the code (commands, options, defaults, file paths, and strings frompackages/cli/src/i18n.ts). For a changed string, find where its key is used (rg "'<key>'" packages) and check the page for that command or feature. Only pages touched by the changes need checking. - Report or update. With
--check-only, list each mismatch as file, what the doc says, and what the code does, then stop. Otherwise fixdocs/en/first, then make the same change indocs/zh-CN/anddocs/ja-JP/so the three stay structurally parallel. Quote notices and errors with the wording ini18n.tsfor each locale; the CLI has no Japanese strings, soja-JPpages quote the English wording. Add new pages to each language'sSUMMARY.mdand the VitePress sidebar. UpdateAGENTS.mdonly if commands, layout or development rules changed. - Verify. Run
pnpm docs:build; it fails on dead links and broken markdown. Fix any errors. - Summarize the pages changed and any mismatches you left alone and why.
Do not delete documented features unless the code shows they were removed. Keep brand names, URLs and command names identical across languages.
Code → documentation map
Paths are relative to docs/<lang>/guide/.
| Code | Page |
|---|---|
packages/core/src/schema/ |
config.md |
packages/cli/src/main.ts (commands, options, exit codes) |
commands.md |
packages/core/src/adapters/<tool>.ts |
That tool's section of tools.md |
packages/core/src/mirror.ts, mirror handling in adapters |
mirrors.md |
packages/core/src/presets.ts, presets/providers.json (format, not entries) |
providers.md |
packages/ui-kit/, packages/cli/src/tui/, packages/web/, packages/cli/src/server.ts |
ui.md |
packages/core/src/io/ (backups), notice.* strings in i18n.ts |
troubleshooting.md |
| Supported tools, install or apply behavior | index.md, and the tools table in docs/<lang>/index.md |
package.json scripts, package layout |
contributing.md |
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 Changed · -414 lines · -9 tokens per session 33947445784c
- 1mo ago First seen · 453 lines · 43 tokens per session scan A c6620157d38a
zcf-update-docs is a skill published in the GitHub repository UfoMiao/zcf (6,079 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 758 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
integrations
NextDNS integration guides for third-party platforms and services. This skill should be used when integrating NextDNS with routers, home automation systems, network management platforms, or other third-party services. It also guides transport selection across DoH, DoT, DoQ, DoH3, IPv6, and legacy DNS. Triggers on…
nextdns-cli
NextDNS CLI client best practices for installation, configuration, and management of DNS-over-HTTPS proxy. This skill should be used when installing NextDNS on routers, servers, or client devices, configuring DNS settings, managing the daemon, or troubleshooting DNS issues. Triggers on tasks involving NextDNS CLI…
nextdns-ui
NextDNS Web UI configuration and management best practices. This skill should be used when configuring NextDNS profiles via the web interface (my.nextdns.io), including security features, privacy lists, parental controls, and monitoring logs.
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-watermark
Steganographic code watermarking for IP defense. Generates multi-layered fingerprints that survive AI rewrites, language changes, renaming, and clean-code passes. Produces timestamped cryptographic commitments for legal proof of authorship. Use when the user wants to watermark a codebase, protect IP, prove code…
cli-audit-data
Audit PostgreSQL database safety in Rust/SQLx applications. Use for schemas, migrations, constraints, indexes, transactions, repositories, state transitions, idempotency, concurrency, queues, multi-tenancy, soft deletion, ledgers, auditability, repair, database incidents, or whenever SQLx and PostgreSQL changes could…