Skip to main content
Glama
Sign In
codex-subagent-for-claude

codex-subagent-for-claude

by Ryen-LTC
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

codex_steer

Steer a running Codex task by appending or correcting instructions so it changes direction after the current step without restarting and preserves completed work. Only works on active tasks.

Instructions

给一个正在运行的任务追加或修正指令，Codex 在当前步骤结束后转向，不用重来，已做的工作保留。只对运行中的任务有效；任务已结束时报错，此时应改用 codex_spawn(thread_id=...) 续问。想让它停下来而不是转向，用 codex_interrupt。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "id": "<id>",
      "prompt": "<prompt>"
    },
    "name": "codex_steer"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes运行中任务的 8 位 id（codex_spawn 返回的）
promptYes追加的指令，只写增量，不用重复原任务

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.2.3
    • addedInput schema / properties / id / description
      Added value: +"运行中任务的 8 位 id（codex_spawn 返回的）"
    • addedInput schema / properties / prompt / description
      Added value: +"追加的指令，只写增量，不用重复原任务"
  2. First observedv0.2.1

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so the safety profile is covered. The description adds meaningful behavior beyond that: the run pivots at the end of the current step, prior work is retained, and calling on a finished task errors. It does not address response format or whether repeated steers compose, keeping it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and effect, then the precondition and the two sibling alternatives in order of relevance. Every sentence carries distinct information with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, but the description covers effect, precondition, failure mode, and alternate routes, which is everything needed to invoke this two-parameter steering tool correctly. Annotations carry the safety profile, so nothing material is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%; both parameters are already documented in the schema (id = 8-digit running task id from codex_spawn, prompt = incremental instruction). The description adds only modest framing about writing incremental instructions, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (append/correct instructions) and resource (a running task), then immediately clarifies the effect: Codex pivots after the current step without restarting and preserves completed work. It distinguishes itself from codex_spawn (continuation) and codex_interrupt (stopping) by name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly bounds usage: only valid for running tasks, errors if the task has ended, and in that case directs the agent to codex_spawn(thread_id=...). It also names the alternative for the opposite intent (codex_interrupt). When/when-not/alternatives are all present.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools