Investigation toolkit for AT Protocol network analysis — bundles MCP tools for ClickHouse data access, domain/IP/URL reconnaissance, content similarity detection, and Ozone moderation labelling, alongside skills codifying investigation methodology and agents orchestrating the full workflow.
Use when you need to query ClickHouse for investigation data — rule hit analysis, account activity patterns, content similarity searches, or temporal analysis. Receives a research question, formulates queries, executes via MCP tools, and returns structured findings with the SQL used. Examples: "find all rule hits for this DID", "show posting patterns for these accounts", "find similar content to this text".
Use when conducting AT Protocol network investigations — from initial discovery through final reporting. Takes an investigation brief, coordinates data gathering by delegating ClickHouse work to the data-analyst subagent, performs recon (domain/IP/URL/whois) directly, and produces formatted reports following B-I-N-D-Ts conventions. Examples: "investigate these accounts", "analyze this coordinated network", "produce a cell deep-dive report on these DIDs".
Understanding the Osprey moderation infrastructure — system architecture, ClickHouse data access, schema reference, and relationship to Ozone labelling. Use when investigating AT Protocol accounts or reviewing rule execution data.
Structured account assessment for AT Protocol investigations. Replaces manual account profiling by defining data collection questions, classification schema, and output format. Produces account_type, confidence, signals, and recommendation. Use when profiling an account of interest during Phase 2 (Characterization) or as a standalone quick assessment.
Narrative classification of co-sharing clusters on AT Protocol. Analyses cluster member content, identifies dominant narratives, coordination signals, shared sources, and likely origin. Distinguishes information operations from organic coordination. Use when a co-sharing cluster is identified during Phase 3 (Linkage) or Phase 4 (Amplification), or as a standalone cluster assessment.
Six-phase investigation methodology for AT Protocol network analysis — from initial discovery through reporting. Covers tool selection, signal identification, evidence standards, and directory conventions. Use when conducting or planning investigations.
Query patterns, safety rules, and performance tips for ClickHouse investigation queries against osprey_execution_results. Use when writing or reviewing ClickHouse queries for investigations.
External network access
Connects to servers outside your machine
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin marketplace for investigating coordinated behaviour on the AT Protocol network, authoring Osprey SML moderation rules, and managing Ozone queues. Built and maintained by Skywatch Blue.
| Plugin | Version | Purpose |
|---|---|---|
| osprey-rules | 0.3.0 | SML rule authoring orchestrator with specialized subagents |
| osprey-rule-investigator | 0.1.0 | Read-only analysis of SML rule projects |
| skywatch-investigations | 0.18.0 | Network investigation toolkit (MCP + skills + agents) |
Add the marketplace to your Claude Code settings:
claude install-plugin github:skywatch-bsky/claude-skills
Individual plugins are registered in .claude-plugin/marketplace.json and loaded by Claude Code from the plugins/ directory.
uv on PATH (used by MCP server installation and osprey-cli)git+ssh:// MCP dependencies)osprey-for-atproto repoOrchestrator plugin for writing, reviewing, and debugging Osprey SML moderation rules. Uses an orchestrator-and-subagents pattern where domain knowledge lives in skills and agents contain only routing logic.
The entry point agent (osprey-rule-writer) dispatches specialized subagents based on user intent:
| Flow | Trigger | Agents involved |
|---|---|---|
| Write | "Write a rule for X" | investigator → planner → impl → reviewer (→ debugger loop) |
| Validate | "Validate my rules" | investigator → reviewer (→ offer debugger) |
| Fix | "Fix this error" | investigator → debugger → reviewer (→ debugger loop) |
| Reference | "What patterns exist?" | Orchestrator loads osprey-sml-reference directly |
| Review | "Review this rule" | Reviewer in ad-hoc mode |
Subagents
Skills (5)
planning-osprey-rules — requirements gathering workflowauthoring-osprey-rules — SML authoring workflowreviewing-osprey-rules — three-layer verification methodologyfixing-osprey-rules — error categories and fix patternsosprey-sml-reference — SML type system, 24 labelling pattern templates, naming conventionsCommand
/osprey-validate [path] — runs uv run osprey-cli push-rules --dry-run| Variable | Required | Purpose |
|---|---|---|
OSPREY_RULES_PATH | No | Path to the Osprey rules project directory (contains main.sml). If unset, the agent asks. |
OSPREY_REPO_PATH | No | Path to the osprey-for-atproto repository. If unset, the agent asks. |
Read-only analysis agent for Osprey SML rule projects — produces structured text reports covering project structure, labels, models, UDFs, and execution graphs without modifying any files.
Used as a subagent by osprey-rules for project state discovery, but can also be invoked standalone.
osprey-for-atproto repo path (required for dynamic UDF discovery; static fallback used otherwise)Investigation toolkit for AT Protocol network analysis. Three-layer architecture: an MCP server for native tool access, skills that codify investigation methodology, and agents that orchestrate workflows.
npx claudepluginhub skywatch-bsky/claude-skills --plugin skywatch-investigationsOrchestrator plugin for writing, reviewing, and debugging Osprey SML moderation rules for atproto. Dispatches specialized subagents (planner, implementor, reviewer, debugger) via a thin coordinator.
Read-only analysis agent that investigates Osprey SML rules projects and produces structured reports on labels, models, UDFs, and execution graphs.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer