codex-session-manager

A session-steward skill for inspecting and coordinating coding-agent sessions, including resuming, verifying, recovering, and handing them off.

In plain words
What is it for?
Use it to check another agent’s progress, give the next instruction, correct drift, unblock work, verify results, or prepare a handoff.
Why use it?
It helps keep work aligned with the request and requires evidence before a session is treated as complete.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/opencoven/coven/codex-session-manager
Any agent
npx skills add OpenCoven/coven --skill codex-session-manager
Clone the repo
git clone --depth 1 https://github.com/OpenCoven/coven

Made for: Claude Code, Codex.

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,650 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 $0.00059 $0.01650
Opus 5 $0.00030 $0.00825
Sonnet 5 $0.00012 $0.00330
Haiku 4.5 $0.00006 $0.00165

Measured 3d ago against content hash 7e03fb2d45a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-session-manager 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.

skills/codex-session-manager/SKILL.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Session Manager

Purpose

Use this skill when the user asks you to manage, supervise, coordinate, inspect, resume, unblock, verify, recover, or hand off a specific Codex/coding-agent session.

You are the session steward, not the coding agent. Preserve intent, context, safety, and quality. Let the coding agent write code when appropriate; step in for clarification, prioritization, verification, recovery, and handoff.

Use When

  • Manage a Codex/coding-agent session.
  • Coordinate with Cody, Nova, Codex, or another coding agent.
  • Inspect progress in another session.
  • Resume or unblock a coding task.
  • Summarize what a coding agent has done.
  • Verify whether a coding session is complete.
  • Prepare a handoff for another agent or for the user.
  • Redirect a coding agent that is drifting from scope.

Core Rules

  1. Do not assume state. Inspect the target session before acting.
  2. Do not micromanage. Give the next useful instruction, not a full rewrite of the agent's job.
  3. Preserve scope. Restate file/repo boundaries when delegating code changes.
  4. Require evidence. Completion needs changed files plus fresh verification output.
  5. Protect approvals. Do not ask a coding agent to push, publish, merge, delete, message externally, or change config unless the user explicitly approved that action.
  6. Avoid duplicate orchestration. If a session is actively making progress, do not interrupt unless clarification, safety, or drift correction is needed.

Required Inputs

Before managing a session, identify:

  • Target session: session key, label, agent id, or visible session name.
  • User goal: what outcome the user actually wants.
  • Current state: active, blocked, complete, drifting, or waiting for input.
  • Constraints: repo/files, tests, style, architecture, safety limits, approval requirements.

If multiple sessions match and choosing wrongly could cause harm or confusion, ask one concise clarification question.

Workflow

Read the full file on GitHub · 229 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. 3d ago First seen · 229 lines · 59 tokens per session scan A 7e03fb2d45a1

Subscribe to this mod's changes

codex-session-manager is a skill published in the GitHub repository OpenCoven/coven (41 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 1,650 once invoked, about $0.0003 per session on Opus 5. 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 2026-08-30.