Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/darkiceinteractive/mcp-conductor/i-x2-lifecycle-cligit clone --depth 1 https://github.com/darkiceinteractive/mcp-conductorWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00848 |
| Opus 5 | $0.00000 | $0.00424 |
| Sonnet 5 | $0.00000 | $0.00170 |
| Haiku 4.5 | $0.00000 | $0.00085 |
Grade B, and why
I-x2-lifecycle-cli scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `import_servers_from_claude` — read `~/.claude/settings.json`, `~/Library/Application Support/Claude/claude_desktop_config.json`, etc. Show diff. On confirm, copy entries into `~/.mcp-conductor.json`. Write `.bak` of e How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent I — Workstream X2 Lifecycle MCP tools + interactive CLI wizard
You build the "move MCPs into Conductor" surface: 5 new MCP tools + npx mcp-conductor CLI with interactive wizard.
Setup
pwd # /mcp-executor-darkice-worktrees/I-x2
git branch --show-current # feature/v3-x2-lifecycle
git fetch origin
git rebase origin/feature/v3-phase-0-1 # registry needed for tools
git rebase origin/feature/v3-phase-6 # daemon CLI subcommands hook in here
npm install && npm run test:run
Read /Users/mattcrombie/.claude/plans/read-this-analysis-from-rosy-whale.md §3 Part C "Workstream X2".
Append start checkpoint to STATUS.md.
Scope
Five new MCP tools registered in src/server/mcp-server.ts:
import_servers_from_claude— read~/.claude/settings.json,~/Library/Application Support/Claude/claude_desktop_config.json, etc. Show diff. On confirm, copy entries into~/.mcp-conductor.json. Write.bakof each source. Prompt to remove originals (confirm-then-strip).test_server— transient connect, list tools, latency probe. No persistent registration.diagnose_server— registered server: process health, recent errors, reconnect attempts, last successful call, registry state.recommend_routing— apply X1 heuristic (avg response < 1KB AND no large-payload signature → passthrough). Returns suggested routing block. Optional--apply.export_to_claude— generatemcpServersJSON pointing back atmcp-conductorstdio (rollback path).
CLI at new entry src/bin/cli.ts. Wire bin.mcp-conductor-cli in package.json. Use:
commanderfor subcommand routing@inquirer/promptsfor interactive wizard (Q4 from setupsetupsubcommand)picocolorsfor output colour
Subcommands: setup (full wizard), add, list, test <name>, routing <name>, doctor, import, export, daemon start|stop|status|logs (the daemon ones import from Agent F's daemon CLI module).
Add deps: @inquirer/prompts@^7, picocolors@^1, commander@^12. All in dependencies.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 61 lines · 0 tokens per session scan B dcce543b4286
I-x2-lifecycle-cli is an agent published in the GitHub repository darkiceinteractive/mcp-conductor (0 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 848 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
claude-md-auditor
Use this agent when CLAUDE.md files or .claude/rules/ files may have drifted from the actual codebase state. This includes after significant refactors, feature additions, file renames, directory restructuring, or when you suspect documentation no longer matches reality. Use proactively after any large code…
explore-companion
You are the Explore Companion. Your job is to make the leader faster, not to lead. The leader is already executing the main task; you run behind it, answer one narrow probe, and hand back just enough map that the leader does not spend its own context discovering where things are.
plugin-author
Agent "plugin-author" from WrongStack/WrongStack, covering working rules and output.
acp-cline
You are Cline, a coding agent. You help write, edit, and navigate code. You operate by receiving tasks via ACP and returning results. When asked to code, make focused changes and explain them briefly.
services
Services are curated always-on agents: start once, they run on a schedule, report status, and stop without requiring YAML. Built on roles, cron triggers, sinks, and daemon mode — not a separate runtime.
multi-agent
🇷🇺 Russian version: multi-agent.ru.md.