sentry-miniapp: Skill for Claude Code

.agents/skills/sentry-miniapp-sdk/SKILL.md

sentry-miniapp-sdk is a skill for Claude Code, Codex from lizhiyao/sentry-miniapp. It costs 69 tokens per session (1,974 once invoked), scanned A, original, MIT.

Setup guidance for using sentry-miniapp, a community Sentry SDK that monitors errors and performance in mini programs. Mini programs are apps running inside platforms such as WeChat, Alipay, or ByteDance, and the SDK also covers frameworks such as Taro and uni-app.

In plain words
What is it for?
Use it when adding error monitoring, performance tracing, offline caching, or source-map support to native or cross-platform mini-program projects.
Why use it?
It helps add monitoring without overlooking platform differences, offline data, source maps, or existing Sentry configuration. The instructions also require checking the current SDK documentation before implementation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is lizhiyao/sentry-miniapp's own configuration. It tells Claude Code and Codex how to work on sentry-miniapp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sentry-miniapp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lizhiyao/sentry-miniapp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lizhiyao/sentry-miniapp/master/.agents/skills/sentry-miniapp-sdk/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lizhiyao/sentry-miniapp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for sentry-miniapp-sdk

README.md
[![agentmods](https://agentmods.dev/badge/skills/lizhiyao/sentry-miniapp/sentry-miniapp-sdk/github.svg)](https://agentmods.dev/skills/lizhiyao/sentry-miniapp/sentry-miniapp-sdk)
Your own site
<a href="https://agentmods.dev/skills/lizhiyao/sentry-miniapp/sentry-miniapp-sdk"><img src="https://agentmods.dev/badge/skills/lizhiyao/sentry-miniapp/sentry-miniapp-sdk/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.

agentmods 80×15 button for sentry-miniapp-sdk

Your own site · 80×15
<a href="https://agentmods.dev/skills/lizhiyao/sentry-miniapp/sentry-miniapp-sdk"><img src="https://agentmods.dev/badge/skills/lizhiyao/sentry-miniapp/sentry-miniapp-sdk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,974 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.01974
Opus 5.5 $0.00028 $0.00790
Sonnet 5.5 $0.00014 $0.00395
Haiku 4.5 $0.00007 $0.00197

Measured 13d ago against content hash 0394e6151632, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sentry-miniapp-sdk 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 13d 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.

.agents/skills/sentry-miniapp-sdk/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sentry Mini Program SDK Setup

Use this skill when a user wants to integrate or troubleshoot sentry-miniapp in a consumer application. Discover the application's runtime, installed SDK and entry point before choosing code. This guide covers the stable 2.x contract.

1. Inspect the consumer

Read project instructions and inspect the relevant application directory. Prefer rg; exclude generated bundles and dependencies when searching source.

rg --files -g 'package.json' -g '*lock*' -g '*project*.json' -g 'app.json' \
  -g '*app.{js,ts,tsx,vue}' -g '*main.{js,ts}' \
  -g '*config.{js,ts,mjs}' -g '!node_modules' -g '!dist'
rg -n 'sentry-miniapp|@tarojs/|@dcloudio/uni-' package.json
rg -n 'Sentry\.init|sentry-miniapp|errorHandler|componentDidCatch' \
  src app.js app.ts -g '!node_modules' -g '!dist'

Adjust search roots to files that exist; these commands illustrate discovery, not a required directory layout.

Determine:

  • Installed version and package manager. Read the lockfile and installed package metadata; a manifest range alone may not identify the resolved version.
  • Release targets. Read framework configuration and platform globals. WeChat's project.config.json, Alipay's mini.project.json, ByteDance's project.tt.json and Baidu's project.swan.json are useful clues. Confirm QQ, DingTalk and Kuaishou from actual target configuration.
  • Framework and entry. Native apps commonly use app.js/app.ts; Taro uses src/app.tsx or its configured entry; Vue 3 uni-app usually initializes from src/main.js/main.ts.
  • Existing monitoring and privacy policy. Preserve working error handlers, integrations, sampling and consent requirements.
  • Sentry deployment and build pipeline. Version support and final JS/map matching affect which features can be verified.

2. Choose the SDK version and features

An unqualified install selects the current stable release; sentry-miniapp@2 selects the stable 2.x line. For an explicitly requested prerelease, verify the available tag or exact version before installing; do not assume a next tag exists. Do not silently migrate an existing 1.x application. Use the version and migration guide, including its fixed 1.x documentation archive.

Read the full file on GitHub · 125 lines

Files

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.

Changes

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.

  1. 13d ago Changed · +2 lines · +4 tokens per session 0394e6151632
  2. 23d ago Changed ffe1a301be7a
  3. 26d ago Changed · -251 lines · +6 tokens per session 32607cc2b3ae
  4. 27d ago Changed · +2 lines 79c4d70a4ea9
  5. 28d ago Changed · +2 lines 7abd7221bc2c
  6. 1mo ago Changed · -5 lines 8d82f3a3f018
  7. 1mo ago Changed · +10 lines cb3983cd965b
  8. 2mo ago Changed 584fc2903784
  9. 2mo ago First seen · 365 lines · 59 tokens per session scan A d1fccf367dcc

Subscribe to this mod's changes

sentry-miniapp-sdk is a skill published in the GitHub repository lizhiyao/sentry-miniapp (712 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 1,974 once invoked, about $0.0003 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.

Related

sentry-miniapp-sdk compared with skills from other repositories

sentry-miniapp-sdk next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sentry-miniapp-sdklizhiyao/sentry-miniappSkill712yesterdayMITA69Claude Code, Codex
error-monitoringzebbern/termstackSkill46mo agononeA59Claude Code, Codex
temps-plugingotempsh/tempsSkill903yesterdayApache-2.0A92Claude Code, Codex
otel-ottldash0hq/agent-skillsSkill993d agoApache-2.0A81Claude Code
integration-rule-engineaozyildirim/AgenaSkill10328d agoMITA67Claude Code, Codex
frontend-performancessheleg/sheleg-devSkill44d agoMITA84Claude Code
honeybadger-mcpvishalzambre/honeybadger-mcpSkill622d agoMITA74Claude Code, Codex