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-recoverygit 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-recovery)<a href="https://agentmods.dev/skills/sun-sunshine06/miniprogram-skills/miniapp-devtools-recovery"><img src="https://agentmods.dev/badge/skills/sun-sunshine06/miniprogram-skills/miniapp-devtools-recovery/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/sun-sunshine06/miniprogram-skills/miniapp-devtools-recovery"><img src="https://agentmods.dev/badge/skills/sun-sunshine06/miniprogram-skills/miniapp-devtools-recovery.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00063 | $0.00450 |
| Opus 5 | $0.00032 | $0.00225 |
| Sonnet 5 | $0.00013 | $0.00090 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
miniapp-devtools-recovery 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 10d 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.
What it actually says
Miniapp Devtools Recovery
Overview
Use this skill when DevTools has polluted the repository or started compiling the wrong thing. Keep the cleanup minimal and restore tracked files before deleting residue.
Quick Start
- Read
references/devtools-recovery-checklist.md. - Inspect
git status, repository root,project.config.json,project.private.config.json, andapp.json. - Decide whether the problem is wrong import root, template residue, stale compile condition, or TypeScript-recognition drift.
- Restore tracked files first, then delete only the generated residue.
- Tell the user exactly which directory to import and which compile mode to use.
Core Rules
- Treat repository root and miniapp code root as separate concerns.
- Prefer restoring tracked files from version control before deleting generated clutter.
- Keep
project.private.config.jsonlocal-only; do not rely on it for shared project truth. - Remove generated template pages or helpers unless the app explicitly depends on them.
- If DevTools complains about missing
.jsfiles while the repo authors in.ts, verify TypeScript recognition before rewriting the app to JavaScript. - If DevTools tries to start from a page not listed in
app.json, suspect a stale custom compile condition first.
Output Format
When answering, keep the result short and operational:
- what DevTools changed
- what should remain in the repo
- what to delete or restore
- what the user must change in DevTools
Resources
references/devtools-recovery-checklist.md: cleanup rules and error-to-cause mappingreferences/example-prompts.md: reusable trigger examples and evaluation notes
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.
- 10d ago First seen · 49 lines · 63 tokens per session scan A a5316914f67e
miniapp-devtools-recovery is a skill published in the GitHub repository Sun-sunshine06/miniprogram-skills (22 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 450 once invoked, about $0.0003 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
ai-skill-create
Create, improve, validate, forward-test, and package Codex skills from a user's brief, examples, files, or instructions. Use when asked to design a new skill, update an existing SKILL.md, add references/scripts/assets, create agents/openai.yaml, validate skill structure, or prepare a skill for…
minimal-skill
Demonstrate a minimal instruction-only Codex skill that drafts concise release notes from a changelog, commit summary, or PR description.
scripted-skill
Demonstrate a scripted Codex skill that normalizes proposed skill names into lowercase kebab-case and validates naming constraints.
example-skill-name
Describe what this skill does and the concrete user requests that should trigger it.
daily-news-report
Automated news aggregation and reporting agent.
scaffold
Analyzes this repository and generates an optimized CLAUDE.md and project-specific Claude Code skills. Auto-invoke when CLAUDE.md is missing, when asked to "scaffold", "initialize claude context", "set up claude", or "generate claude files".