H-x1-passthrough

H-x1-passthrough is an agent for Claude Code from darkiceinteractive/mcp-conductor. It costs 0 tokens per session (630 once invoked), scanned A, original, MIT.

An agent for adding selected direct tools to a Conductor MCP server. MCP is a standard way for an AI agent to call external tools.

In plain words
What is it for?
Use it when implementing the passthrough adapter, its server startup registration, default routing rules, and related tests.
Why use it?
It lets designated tools bypass the code-execution route while keeping the information supplied by the upstream tool registry.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/mattcrombie/.claude/plans/read-this-analysis-from-rosy-whale.md.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

Wrote 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.

agentmods badge for H-x1-passthrough

README.md
[![agentmods](https://agentmods.dev/badge/agents/darkiceinteractive/mcp-conductor/h-x1-passthrough.svg)](https://agentmods.dev/agents/darkiceinteractive/mcp-conductor/h-x1-passthrough)
Your own site
<a href="https://agentmods.dev/agents/darkiceinteractive/mcp-conductor/h-x1-passthrough"><img src="https://agentmods.dev/badge/agents/darkiceinteractive/mcp-conductor/h-x1-passthrough.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 630 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00630
Opus 5 $0.00000 $0.00315
Sonnet 5 $0.00000 $0.00126
Haiku 4.5 $0.00000 $0.00063

Measured 5d ago against content hash d5fc85653885, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

H-x1-passthrough 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 5d 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.

_plans/v3-enhancements/agents/H-x1-passthrough.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent H — Workstream X1 Passthrough adapter

You expose registry-annotated routing: "passthrough" tools as first-class Conductor MCP tools (bypassing execute_code), with full upstream annotations preserved. Closes IBKR analysis findings #2 and #3.

Setup

pwd  # /mcp-executor-darkice-worktrees/H-x1
git branch --show-current  # feature/v3-x1-passthrough
git fetch origin && git rebase origin/feature/v3-phase-0-1   # registry must be in
npm install && npm run test:run

Read /Users/mattcrombie/.claude/plans/read-this-analysis-from-rosy-whale.md §3 Part C "Workstream X1".

Append start checkpoint to STATUS.md.

Scope

Files:

  • src/server/passthrough-registrar.ts (NEW) — at server start, iterate registry.getAllTools(), register a <server>__<tool> MCP tool for each routing: "passthrough" entry. Wire to mcpHub.callTool() directly (bypass Deno).
  • src/server/mcp-server.ts — call registerPassthroughTools() after registry.refresh().
  • src/registry/built-in-recommendations.ts (NEW) — default routing for known servers. Ship with:
    • github: routing.passthrough = ['get_me', 'list_repositories']; rest execute_code.
    • filesystem: routing.passthrough = ['read_file', 'list_directory']; write_file and delete stay execute_code.
    • brave-search: routing.passthrough = ['brave_web_search']. Apply only when no user-config override present.

Tool name format: <server>__<tool> (double underscore, namespaced). Carry through upstream readOnlyHint, destructiveHint, idempotentHint, openWorldHint, title, description.

Acceptance

  • routing: "passthrough" tools appear in tools/list from Conductor.
  • Annotations match upstream values.
  • Default routing for newly added (unknown) servers is execute_code (backwards compat).
  • Built-in recommendations apply at startup; user config overrides them.
  • Tests in test/unit/passthrough-registrar.test.ts (~6 cases) all pass.

Commit pattern

feat(v3-x1): passthrough registrar that reads registry annotations
feat(v3-x1): built-in routing recommendations for github/filesystem/brave-search
feat(v3-x1): wire registrar into mcp-server startup after registry.refresh
test(v3-x1): passthrough registrar test suite

Read the full file on GitHub · 51 lines

Changes

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.

  1. 5d ago First seen · 51 lines · 0 tokens per session scan A d5fc85653885

Subscribe to this mod's changes

H-x1-passthrough 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 630 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.