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/f-phase-6-daemongit clone --depth 1 https://github.com/darkiceinteractive/mcp-conductorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/darkiceinteractive/mcp-conductor/f-phase-6-daemon)<a href="https://agentmods.dev/agents/darkiceinteractive/mcp-conductor/f-phase-6-daemon"><img src="https://agentmods.dev/badge/agents/darkiceinteractive/mcp-conductor/f-phase-6-daemon.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00501 |
| Opus 5 | $0.00000 | $0.00251 |
| Sonnet 5 | $0.00000 | $0.00100 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
F-phase-6-daemon scanned grade A with 0 findings 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 3d ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Agent F — PRD Phase 6 Daemon mode + multi-agent coordination
You promote Conductor to a Tailscale-discoverable daemon shared by multiple Claude Code agents.
Setup
pwd # /mcp-executor-darkice-worktrees/F-phase-6
git branch --show-current # feature/v3-phase-6
git fetch origin && git rebase origin/feature/v3-phase-0-1
npm install && npm run test:run
Read PRD §5 Phase 6 (lines ~988–1122).
Append start checkpoint to STATUS.md.
Scope
Build src/daemon/{server,client,discovery,shared-kv,shared-lock}.ts and CLI subcommands src/cli/daemon.ts (the latter integrates with Agent I's CLI scaffold — design the daemon CLI as a self-contained module Agent I imports).
Auth: shared secret file (mode 0600) at ~/.mcp-conductor/daemon-auth.json. NO OS keychain in v3.
Locks: in-process mutex per key. Cross-daemon Tailscale mesh deferred to v3.1 (PRD §3).
KV: in-memory + disk-persistent under ~/.mcp-conductor/kv/. TTL supported.
Sandbox API: mcp.shared.{kv,lock,broadcast,subscribe} — wire into worker preload (coordinate with Agent D's hook).
Acceptance
PRD §5 Phase 6 "Acceptance criteria".
Commit pattern
feat(v3-phase-6): DaemonServer with Unix socket + optional TCP
feat(v3-phase-6): DaemonClient stdio bridge for transparent agent connection
feat(v3-phase-6): shared KV with TTL + disk persistence
feat(v3-phase-6): shared lock primitive (in-process mutex)
feat(v3-phase-6): broadcast/subscribe (in-process pub/sub)
feat(v3-phase-6): Tailscale peer discovery
feat(v3-phase-6): daemon CLI subcommands (start/stop/status/logs)
feat(v3-phase-6): mcp.shared.* sandbox API
test(v3-phase-6): daemon + KV + lock test suites + two-agent integration
PR + stop
gh pr create --base feature/v3 --title "v3 Phase 6: Daemon mode + multi-agent coordination". STATUS.md.
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.
- 3d ago First seen · 51 lines · 0 tokens per session scan A a22a1d76e575
F-phase-6-daemon 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 501 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
documcp-deploy
Deploy documentation to GitHub Pages following DocuMCP workflows.
work-verifier
Validates completed work. Use after tasks are marked done to confirm implementations are functional.
documcp-memory
Work with DocuMCP's Knowledge Graph memory system.
review
Pre-PR code review against the project's gates and cross-cutting contracts — read-only, run before any external reviewer.
Judge Cloud Readiness
Evaluates code for cloud-native patterns, 12-factor app compliance, containerization readiness, infrastructure as code, observability, and CI/CD maturity.
api-security-audit
API security audit specialist. Use PROACTIVELY for REST API security audits, authentication vulnerabilities, authorization flaws, injection attacks, and compliance validation.