15,408 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Use when a code change has multiple plausible implementation paths, high regression risk, uncertain root cause, or unclear tradeoffs. Creates isolated candidate implementations, runs comparable verification across each candidate, compares evidence, and applies the best proven approach while preserving user changes.
REQUIRED when user mentions a Drupal module + error/bug/issue - even without stack traces. Trigger on: (1) " module has an error/bug/issue", (2) "Acquia/Pantheon/Platform.sh" + module problem, (3) any contrib module name (metatag, webform, mcp, paragraphs, etc.) + problem description. Searches drupal.org BEFORE you…
Use whenever code navigation, analysis, refactoring, or diagnostics are needed on a project that has a Language Server Protocol implementation. Covers all 29 lsp MCP tools exposed by lsp-mcp-server (TypeScript, Python, Rust, Go, C/C++, Ruby, PHP, Elixir, Kotlin, Java, and any user-configured language). Use it instead…
Fix CI failures and performance regressions for a Julia package PR by iterating - triage the latest CI results, fix one root cause, verify locally, push. Use when a PR's GitHub Actions or Buildkite CI is failing, or when CI jobs run slower than they do on the main branch. Verifies CPU and GPU compilation locally…
Read a SQL Server execution plan (.sqlplan / showplan XML) and explain what is actually slow, and why. Prevents the standard wrong conclusions: reading cost percentages as measurements, ranking operators by cumulative time, comparing estimated to actual rows without dividing by executions, calling scans defects, and…
★not rated 21▲
+1 1mo agoA
tokens not measured
originalMIT
See the full type-inference chain of any PHP value in PHPStan — every assignment, parameter binding, narrowing, and read up to the failing line. Lets Claude Code fix PHPStan errors with upstream type evidence instead of guesses.
★not rated 20 3mo agoA
tokens not measured
originalMIT
CodeEraser passive guard + erase skill: a winnowing clone index behind a per-project daemon intercepts T1/T2 duplicate writes at PreToolUse, audits net LOC + touched duplicates at Stop, and reports health at SessionStart; the erase skill walks findings to safe, re-gated deletions. Gradual modes observe/warn/ask/deny…
★not rated 20
changed 2d agoA
tokens not measured
originalApache-2.0
Use when building flowchart pipelines with footprintjs — stage functions, decider branches, selectors, subflows, loops, narrative traces, recorders, redaction, contracts, and LLM-ready output. Also use when someone asks how footprint.js works or wants to understand the library.
This project has hypergrep installed globally. Use it instead of grep/ripgrep when you need structural understanding of code (function bodies, call graphs, impact analysis). For simple text searches, ripgrep is fine.
Diagnose and fix bugs using runtime execution traces. Use when debugging errors, analyzing failures, or finding root causes in Python, Node.js, or Java applications.
Covers building, extending, debugging, and maintaining Foundry VTT modules for v13+. This skill applies when scaffolding a new module, writing custom Actor/Item types with TypeDataModel, building ApplicationV2 sheets or dialogs, registering hooks or settings, implementing socket communication, extending the canvas…
A performance-monitoring workflow for Minecraft Bedrock mods that uses Tracy, a tool that records where a running program spends CPU time.
★not rated 20▲
+2 1mo agoA92 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: