claude

agent-code-intel

Operating skill for the live-code grounding layer: resolve symbols, references, and signatures through a Serena/LSP MCP server instead of grepping or guessing. Pairs with the agent-kb plugin (KB owns the concept-to-symbol binding; the LSP owns the live resolution).

0 on GitHubby Sergei Fedorovv0.1.0MITupdated 3 months ago

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin agent-code-intel in zmij/agent-code-intel. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (1)

  • code-intelligence

    Resolve a symbol to its live location, signature, and references in the current worktree via the Serena MCP server (LSP-over-MCP). AUTO-TRIGGER when about to claim a file path, line number, signature, or call site for any class, method, or function — go through Serena instead of grepping or guessing

View source on GitHub

Similar plugins

gitnexus

claudecodex

Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.

12 skills · 1 MCP server · hooks

abhigyanpatwari/GitNexus 48,482

GC AI

claude

Work in your GC AI legal knowledge base from Claude: upload documents, run review playbooks, and ask questions grounded in your own files, all as you.

3 skills · 1 agent · 1 MCP server

anthropics/claude-plugins-official 47,076

documentation-standards

claudecodex

HADS (Human-AI Document Standard) — semantic tagging convention for docs that work for both humans and AI models — plus the grounded-vault pattern for provenance-linked, drift-checked knowledge stores.

2 skills

wshobson/agents 42,461

Maven Bio

claude

Evidence-backed BioPharma research workflows over Maven Bio's drug, trial, company, and deal knowledge graph. Skills for competitive pipelines, indication landscapes, asset profiles, deal and financing activity, and evidence synthesis grounded in FDA, SEC, clinical, and press sources. Requires a Maven Bio account.

16 skills · 1 agent · 1 MCP server

anthropics/knowledge-work-plugins 35,601

zero-hallucination-coder

claude

A disciplined coding pipeline that grounds code in verified structure before a line is written: Discuss -> Map -> Decompose -> Execute -> Verify, with a lazy-senior-dev YAGNI ladder that deletes unnecessary code first. No invented APIs, no assumed imports, no placeholder code. Opt-in for high-stakes, complex, or multi-file work; not for trivial edits. Synthesizes four MIT/open-source projects (Ralph atomic loop, GSD Core context engineering, Graphify KNOWN/INFERRED/UNKNOWN mapping, Ponytail lazy-senior hierarchy). Contributed via PR #854.

1 skill

alirezarezvani/claude-skills 29,725

google-cloud-developer

claudecodex

Core Google Cloud guidance for coding agents: first-project onboarding, authentication and credential selection, and safety-critical validation for gcloud CLI commands. Includes the Google Developer Knowledge MCP server for grounded, up-to-date Google Cloud documentation.

5 skills · 1 MCP server

google/skills 24,091

Maintain agent-code-intel?

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.

claude & codex pluginslisted