superpowers
claudecodexCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Detect the repo, audit or initialize Sentry (errors, tracing, profiling, replay, logs, metrics, crons, uptime, releases, source maps, alerts, AI monitoring), apply approved changes, and prove them with a live event. CLI-first on the sentry v4 CLI.
Plugin sentry from marketplace plugin-sentry in yigitkonur/plugin-sentry. Commands read from the repo's manifest — 18 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
applyImplement the approved Sentry findings (one commit per group, fix-safety protocol), then verify them with a live event and clean up.
auditAudit the Sentry setup in this repo (and optionally the Sentry org): find what is missing, wrong or risky across errors, tracing, profiling, replay, logs, crons, releases, source maps, privacy and more, then offer to fix it.
cleanRemove the plugin's artifacts from this repo (.sentry-plugin/, leftover temporary trigger files, the .gitignore line it added). Shows what would go first.
doctorCheck that this machine is ready for Sentry work: which CLI is installed, login and scopes, org region, git state, and whether Sentry's own plugins are present.
ground-rulesUse before writing or reviewing Sentry configuration or SDK setup: sentry.init, Sentry.init, sentry_sdk.init, sentry.client/server/edge config, instrumentation.ts, .sentryclirc, sentry.properties, SENTRY_DSN or SENTRY_AUTH_TOKEN, sentry or sentry-cli CI steps. How to work with Sentry here: look opti
initSet up Sentry properly in a repo that has none: picks the install route, proposes the base setup plus extras that fit, applies only what you approve, and proves it with a live event.
orgAudit the Sentry organization behind this repo (projects, keys, filters, scrubbing, spike protection, alerts, monitors, releases, source maps, ownership, usage, Seer settings) with read-only probes, then apply only the org changes you approve.
policyAnswer the privacy, org-access, environment, volume and product questions that drive every audit and setup. Always asks, even if you answered before.
startSet up, check or fix Sentry in this repo. Detects the stack, decides between auditing an existing setup and initializing a missing one, and walks it through to a verified result.
triageUse when the user asks why something is failing or erroring in production, asks for the top or recent Sentry errors or regressions, mentions a Sentry alert, or names a Sentry issue (short id like API-7 or a sentry.io issues URL). Walks the CLI funnel rank, view, corroborate; Seer only on request. No
verifyProve applied Sentry changes with a live marked event: arrival, readable stack trace, privacy scan of the arrived payload. Claims only the verification rung actually reached.
auditorRead-only Sentry auditor for one unit and one product group of a repo (or the Sentry org). Dispatched by the audit and init flows; it writes only through sentry-ctx finding add and coverage set. Do not use for general code review.
implementerApplies approved Sentry findings for one unit and one product group, one commit per group, following the fix-safety protocol. Dispatched by the apply flow; never invoked for unapproved work.
verifierIndependent proof for applied Sentry findings: emits a marked event from the real app, waits for it in Sentry, checks readability and privacy, and records the highest verification rung reached with evidence. Dispatched by the verify flow.
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" session-start
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" guard-write
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" gate-bash
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" stale-api
"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh" stop-gate
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents
3 skills · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Use Alibaba Open Code Review from local Codex.
2 skills
Claude Code skill for creating and presenting Slidev slidedecks
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.