From consensus-loop
Runs consensus-loop CLI tools for codebase analysis (symbols, deps, audits, coverage), RTM ops (parse/merge/query), FVM tasks (generate/validate) via Bash.
npx claudepluginhub berrzebb/claude-plugins --plugin consensus-loopThis skill is limited to using the following tools:
CLI interface for the 9 deterministic analysis tools that power the consensus-loop workflow. These tools run via `tool-runner.mjs` — same logic as the MCP server, but invoked through Bash instead of JSON-RPC.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Guides MCP server integration in Claude Code plugins via .mcp.json or plugin.json configs for stdio, SSE, HTTP types, enabling external services as tools.
CLI interface for the 9 deterministic analysis tools that power the consensus-loop workflow. These tools run via tool-runner.mjs — same logic as the MCP server, but invoked through Bash instead of JSON-RPC.
${CLAUDE_PLUGIN_ROOT}/scripts/tool-runner.mjs
Invocation pattern:
node ${CLAUDE_PLUGIN_ROOT}/scripts/tool-runner.mjs <tool_name> --param value ...
Add --json to any command for structured JSON output instead of formatted text.
| Need | Tool | Reference |
|---|---|---|
| Find functions/classes/types with line ranges | code_map | code-map.md |
| Map import/export dependencies, detect cycles | dependency_graph | dependency-graph.md |
Scan for as any, hardcoded values, console.log | audit_scan | audit-scan.md |
| Get per-file test coverage percentages | coverage_map | coverage-map.md |
| Read RTM rows, filter by req_id or status | rtm_parse | rtm-parse.md |
| Merge worktree RTM files into base | rtm_merge | rtm-merge.md |
| Query audit verdict history, detect patterns | audit_history | audit-history.md |
| Generate FE×API×BE×Auth verification matrix | fvm_generate | fvm-generate.md |
| Execute FVM rows against live server | fvm_validate | fvm-validate.md |
node ${CLAUDE_PLUGIN_ROOT}/scripts/tool-runner.mjs# Symbol index for a directory
node ${CLAUDE_PLUGIN_ROOT}/scripts/tool-runner.mjs code_map --path src/
# Dependency graph with cycle detection
node ${CLAUDE_PLUGIN_ROOT}/scripts/tool-runner.mjs dependency_graph --path src/ --depth 3
# Pattern scan for type-safety issues
node ${CLAUDE_PLUGIN_ROOT}/scripts/tool-runner.mjs audit_scan --pattern type-safety
# Parse RTM, filter by requirement ID
node ${CLAUDE_PLUGIN_ROOT}/scripts/tool-runner.mjs rtm_parse --path docs/rtm.md --req_id EV-1
# Audit history summary with risk patterns
node ${CLAUDE_PLUGIN_ROOT}/scripts/tool-runner.mjs audit_history --summary
# FVM generation
node ${CLAUDE_PLUGIN_ROOT}/scripts/tool-runner.mjs fvm_generate --path /project/root
--json flag outputs structured JSON for programmatic useEvery MCP tool call maps 1:1 to a CLI command:
| MCP Call | CLI Equivalent |
|---|---|
mcp__consensus-loop__code_map({path: "src/"}) | node tool-runner.mjs code_map --path src/ |
mcp__consensus-loop__dependency_graph({path: "src/"}) | node tool-runner.mjs dependency_graph --path src/ |
mcp__consensus-loop__audit_scan({pattern: "all"}) | node tool-runner.mjs audit_scan --pattern all |
mcp__consensus-loop__rtm_parse({path: "x.md"}) | node tool-runner.mjs rtm_parse --path x.md |
The output format is identical — same text, same summary.