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 Sun-sunshine06/miniprogram-skills --skill miniapp-devtools-cli-repairgit clone --depth 1 https://github.com/Sun-sunshine06/miniprogram-skillsWrote 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/sun-sunshine06/miniprogram-skills/miniapp-devtools-cli-repair)<a href="https://agentmods.dev/skills/sun-sunshine06/miniprogram-skills/miniapp-devtools-cli-repair"><img src="https://agentmods.dev/badge/skills/sun-sunshine06/miniprogram-skills/miniapp-devtools-cli-repair.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00076 | $0.00621 |
| Opus 5 | $0.00038 | $0.00311 |
| Sonnet 5 | $0.00015 | $0.00124 |
| Haiku 4.5 | $0.00008 | $0.00062 |
Grade A, and why
miniapp-devtools-cli-repair 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 7d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Miniapp Devtools Cli Repair
Overview
Use this skill when the user needs CLI-visible evidence from WeChat DevTools. Treat the official CLI as the primary observability surface for compile and preview failures.
Quick Start
- Read
references/cli-repair-playbook.md. - Confirm the official DevTools CLI exists and can print help.
- Use
opento establish IDE connectivity and the live service port. - Use
previewas the primary mini program compile check. - Classify the result as:
- CLI-visible and auto-fixable
- CLI-visible but not safe to auto-fix
- host or account blocker
- outside preview scope and better handled by GUI or service-level debugging
Core Rules
- Prefer the official WeChat DevTools CLI over screenshots for first-pass diagnosis.
- Treat CLI output, exit code, process state, and local logs as primary evidence.
- For miniapp compile diagnosis, prefer
previewoverengine build. - Use
openfirst when the live service port is unknown or the current IDE session is suspect. - Auto-fix only repository-scoped problems such as root-path drift, page-path mismatch, or small syntax issues surfaced with exact locations.
- If
previewis already green or the remaining blocker is a page-siderequest:fail, do not keep grinding CLI repair; move to GUI/runtime or service debugging. - Do not claim full coverage when the error exists only in GUI-only panels, runtime requests, or compile-mode menus.
Auto-Fix Boundary
Apply fixes automatically only when they are coherent and local to the repo:
- repair
project.config.json - repair
tsconfig.json - repair
app.json - delete wrong-root residue
- restore tracked files
- replace a pinpointed unsupported syntax form with an equivalent narrow fix
Do not auto-fix without explicit user direction when the change would alter app strategy, publish state, backend settings, or broad syntax across the repo.
Output Format
When answering, keep the result operational:
- what the CLI exposed
- whether the issue is auto-fixable
- what was changed or what further evidence is still needed
- the next command or user action
What ships with it
3 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.
- 7d ago First seen · 67 lines · 76 tokens per session scan A 1356e20b2b9f
miniapp-devtools-cli-repair is a skill published in the GitHub repository Sun-sunshine06/miniprogram-skills (21 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 621 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.
systematic-debugging
Structured debugging methodology — use before proposing fixes for any error or failure. Covers: code bugs, build errors, deploy failures, config conflicts, dependency issues, infra problems. Also use when previous fix attempts failed or root cause is unclear.
error-translator
A Chinese-language assistant that translates English programming errors and explains what they mean. It covers common errors from languages and frameworks including Python, JavaScript, TypeScript, Java, and others.
eslint-fix
A project-aware assistant for finding and fixing ESLint errors, warnings, and configuration compatibility problems. ESLint is a tool that checks JavaScript and TypeScript code for style and common mistakes.
perf-profiler
A performance investigation guide that uses repeatable measurements and profiling evidence to find where software spends time or resources. Profiling records runtime activity such as CPU use, memory use, database work, or network delays.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…