# io.github.icohangar-ops/agent-conductor (npm · @cubiczan/agent-conductor) AGENTS.md + skills MCP with CHP R0 gate and adversary decision tools. - Trust score: 70/100 (medium) - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-08-23 ## Components - npm · `@cubiczan/agent-conductor`: 70/100 (this document), [markdown](https://verifymcp.io/servers/icohangar-ops-agent-conductor/cubiczan-agent-conductor.md), [page](https://verifymcp.io/servers/icohangar-ops-agent-conductor/cubiczan-agent-conductor) ## Channel facts - Registry: `npm` - Package: `@cubiczan/agent-conductor` - Version: `0.1.0` - Transport: `stdio` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-08-23. - **Supply Chain Security**: 98/100 - No malware found by supply-chain analysis. - No known CVEs affecting this package version or its production dependencies. - No install/post-install scripts declared. - 30 of 96 dependencies flagged as unhealthy. - **Provenance & Transparency**: 45/100 - Source repository is publicly reachable at the declared URL. - Provenance check failed: no build-provenance attestation is published. - Clear OSI-approved license (MIT). - Actively maintained (last published 1 days ago). - Disclosure check failed: no security disclosure policy was found in the source repository. - **Schema Quality & AI Usability**: 84/100 - AI-judged instruction clarity (excellent). - Tool/resource definitions use about 562 tokens (~80/item across 7 items; 7 tools + 0 resources), lean. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 0/100 - Stability not yet verified: not enough scan history yet (needs a 30-day window). - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. **Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm. ## Install ### How do I install the io.github.icohangar-ops/agent-conductor MCP server? io.github.icohangar-ops/agent-conductor runs locally as an npm package, launched with npx -y @cubiczan/agent-conductor. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation. ### Claude ```bash claude mcp add icohangar-ops-agent-conductor -- npx -y @cubiczan/agent-conductor ``` ### Cursor ```json { "mcpServers": { "icohangar-ops-agent-conductor": { "command": "npx", "args": [ "-y", "@cubiczan/agent-conductor" ] } } } ``` ### VS Code ```json { "servers": { "icohangar-ops-agent-conductor": { "command": "npx", "args": [ "-y", "@cubiczan/agent-conductor" ] } } } ``` ### Codex ```bash codex mcp add icohangar-ops-agent-conductor -- npx -y @cubiczan/agent-conductor ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "icohangar-ops-agent-conductor": { "type": "local", "command": [ "npx", "-y", "@cubiczan/agent-conductor" ], "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add icohangar-ops-agent-conductor --command npx --arg -y --arg @cubiczan/agent-conductor ``` ### Hermes ```yaml mcp_servers: icohangar-ops-agent-conductor: command: "npx" args: ["-y", "@cubiczan/agent-conductor"] ``` ### Netclaw ```json { "McpServers": { "icohangar-ops-agent-conductor": { "Transport": "stdio", "Command": "npx", "Arguments": [ "-y", "@cubiczan/agent-conductor" ] } } } ``` ### Vellum ```bash assistant mcp add icohangar-ops-agent-conductor -t stdio -c npx -a -y @cubiczan/agent-conductor ``` ### Other ```json { "mcpServers": { "icohangar-ops-agent-conductor": { "command": "npx", "args": [ "-y", "@cubiczan/agent-conductor" ] } } } ``` ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-08-23 (score 70, +15) - [security improvement] Malware scan: unverified → pass ### 2026-08-22 (score 55) First indexed and scored. ## MCP tools (7) ### `contract_load` (~75 tokens) Compile an AGENTS.md operating manual into a structured agent contract: mission, non-negotiable rules, layer responsibilities, verification gates, recommended skills, and out-of-scope list. Pass a file path or a project directory (defaults to the current working directory). Input parameters: - `path` (string): AGENTS.md path or project root ### `contract_verification` (~60 tokens) Return the verification gates from a project's agent contract — the named checklists and shell commands that must pass before work is handed off. Run these and confirm success before declaring any task complete. Input parameters: - `path` (string): AGENTS.md path or project root ### `skills_list` (~68 tokens) Discover SKILL.md skills visible from a project root (project-scope .conductor/.claude/.cursor skill dirs, then personal ones). Returns metadata only (~100 tokens per skill); use skill_load for the full body. Input parameters: - `projectRoot` (string): Project root (defaults to cwd) ### `skill_load` (~68 tokens) Load the full SKILL.md body for a named skill — the on-demand half of progressive disclosure. Call only when the current task matches the skill's description. Input parameters: - `name` (string, required): Skill name as returned by skills_list - `projectRoot` (string): Project root (defaults to cwd) ### `decision_gate` (~107 tokens) Run the Consensus Hardening Protocol R0 gate on a proposed decision: is it solvable, scoped, valid, and worth making at all? Any FATAL answer returns HALT — stop and reframe before doing the work. Input parameters: - `scoped` (boolean, required): Is the scope explicitly bounded? - `solvable` (boolean, required): Can this problem actually be solved? - `valid` (boolean, required): Is the current state accurately understood? - `worth_it` (boolean, required): Do the stakes justify the work? ### `decision_adversary` (~105 tokens) Run a one-shot Consensus Hardening Protocol adversarial pass against a claim or proposed change: CHP attacks its foundations, scores them 0-100, and returns findings plus a session status (EXPLORING / HALT / REFRAME_REQUIRED). Use before locking any high-stakes decision. Input parameters: - `claim` (string, required): The claim or decision to attack - `context` (string): Supporting context for the claim - `high_stakes` (boolean): Default true ### `engine_status` (~79 tokens) Health/readiness probe for the CHP decision engine (Python subprocess). By default returns a cheap readiness snapshot (running, last exit code, restart-backoff state) WITHOUT spawning Python. Pass probe=true to also issue a live ping that warms/spawns the subprocess. Input parameters: - `probe` (boolean): Issue a live ping (spawns the subprocess). Default false. ## Diagnostics Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/icohangar-ops-agent-conductor/cubiczan-agent-conductor#diagnostics ## Score history - 2026-08-23: 70 - 2026-08-22: 55 ## Common questions ### What is the io.github.icohangar-ops/agent-conductor MCP server? io.github.icohangar-ops/agent-conductor is an MCP server listed in the public MCP registry as io.github.icohangar-ops/agent-conductor. AGENTS.md + skills MCP with CHP R0 gate and adversary decision tools. This page covers its npm package (@cubiczan/agent-conductor). ### Is the io.github.icohangar-ops/agent-conductor MCP server safe to use? io.github.icohangar-ops/agent-conductor scores 70 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 August 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm. ### What tools does the io.github.icohangar-ops/agent-conductor MCP server expose? io.github.icohangar-ops/agent-conductor exposes 7 tools: contract_load, contract_verification, skills_list, skill_load, decision_gate, and 2 more. Their descriptions and schemas cost roughly 562 tokens of context every time the server is loaded. ### Is the io.github.icohangar-ops/agent-conductor MCP server still maintained? io.github.icohangar-ops/agent-conductor is still listed as active in the MCP registry. We last reached this channel on 23 August 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced. ### What licence is the io.github.icohangar-ops/agent-conductor MCP server under? io.github.icohangar-ops/agent-conductor declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls. ## Links - npm package: https://www.npmjs.com/package/@cubiczan/agent-conductor - Socket report: https://socket.dev/npm/package/@cubiczan/agent-conductor - Repository: https://github.com/icohangar-ops/agent-conductor - Changelog RSS feed: https://verifymcp.io/servers/icohangar-ops-agent-conductor/cubiczan-agent-conductor.xml - Changelog JSON feed: https://verifymcp.io/servers/icohangar-ops-agent-conductor/cubiczan-agent-conductor.json - HTML version of this page: https://verifymcp.io/servers/icohangar-ops-agent-conductor/cubiczan-agent-conductor