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 agentmods add skills/pidbid/hbuilder-skills/hbuilder-clinpx skills add Pidbid/hbuilder-skills --skill hbuilder-cligit clone --depth 1 https://github.com/Pidbid/hbuilder-skillsWhat 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 | $0.00098 | $0.01029 |
| Opus 5 | $0.00049 | $0.00515 |
| Sonnet 5 | $0.00020 | $0.00206 |
| Haiku 4.5 | $0.00010 | $0.00103 |
Grade A, and why
hbuilder-cli 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HBuilder CLI
Core Rule
Resolve HBuilderX cli.exe before every CLI workflow. Search only common install locations. Do not read environment variables, user config files, or project-local CLI config files. If cli.exe is not found, stop and report every searched path.
Use scripts/hbuilder_cli_probe.ps1 for discovery and basic project inspection. The script emits JSON that includes the resolved CLI path, searched paths, version/help status, and uni-app project markers.
Always respond to the user in Chinese. Keep command names, file paths, platform identifiers, and error excerpts unchanged when they are more accurate in their original form.
Workflow
- Run the probe from the user's project directory or pass
-ProjectPath. - If
foundis false, stop and report the searched paths. - If HBuilderX is not running and CLI output says
未检测到已打开的HBuilderX, runcli.exe openonce, then retry the requested help or workflow command. - Check the project markers before running project commands. A uni-app project normally has
manifest.jsonandpages.jsonat the project root or undersrc/. - Choose the CLI command family from the user intent.
- Run the command with the absolute
cli.exepath and absolute project path. - For run, publish, pack, or troubleshooting tasks, collect the direct CLI output first. If the result failed or is unclear, immediately query
logcat <target> --project <path> --mode lastBuildor the target-specific log command before proposing a fix. - Use CLI output and logs to locate the failing file, platform setting, dependency, or manifest/pages configuration. Edit the project only after the log-backed cause is clear.
- Re-run the smallest relevant CLI verification after a fix, then summarize the command, exit code, key log lines, changed files, generated artifacts, and any remaining blocker.
Intent Map
- Inspect CLI/project: run the probe, then read
references/hbuilder-cli.md. - Run to platform: use
launch <target> --project <path>. Targets includeweb,mp-weixin,mp-alipay,mp-baidu,mp-toutiao,mp-qq,app-android,app-ios,app-harmony, andmp-harmony. - Publish/build artifacts: use
publish <target> --project <path>after reading target options from CLI help orreferences/hbuilder-cli.md. - Cloud App package: use
packorpack <target>only after checking account, certificate, package id, and upload side effects. - Log-driven repair: after a failed run/build/publish, preserve the CLI output, fetch
logcat <target> --project <path> --mode lastBuild, identify the actionable error, patch the project, and re-run the smallest relevant CLI command. - Logs: use
logcat <target> --project <path>with--mode prevBuild,lastBuild, orfull. - Devices: use
devices list --platform <target-family>before App or Harmony launch flows. - LSP diagnostics: use
lsp lint --file <file> --project <path> [--platform ...]. - uni_modules: use
uni_modules --list|--download|--upgrade --project <path>.
What ships with it
5 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.
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 First seen · 53 lines · 98 tokens per session scan A e04a66bd7844
hbuilder-cli is a skill published in the GitHub repository Pidbid/hbuilder-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 98 tokens to every session and 1,029 once invoked, about $0.0005 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
edge-to-edge
Use this skill to migrate your Jetpack Compose app to add adaptive edge-to-edge support and troubleshoot common issues. Use this skill to fix UI components (like buttons or lists) that are obscured by or overlapping with the navigation bar or status bar, fix IME insets, and fix system bar legibility.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
flutter-fix-layout-issues
Fixes Flutter layout errors (overflows, unbounded constraints) using Dart and Flutter MCP tools. Use when addressing "RenderFlex overflowed", "Vertical viewport was given unbounded height", or similar layout issues.
referral-program
When the user wants to design, launch, or optimize an in-app referral / invite / share-to-earn program — including reward structure, mechanics, fraud prevention, deep link setup, and viral coefficient measurement. Use when the user mentions "referral program", "invite a friend", "refer and earn", "share to earn"…
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
ios-hig-design
Design native iOS interfaces following Apple Human Interface Guidelines. Use when the user mentions "iPhone app", "iPad layout", "SwiftUI", "UIKit", "Dynamic Island", "safe areas", "HIG compliance", "SF Symbols", "haptic feedback", "iOS accessibility", "make my app feel native", or "follow Apple design guidelines".…