How do I install the Codesession skill?

Run npx skillmds@latest add tomevault-io/codesession in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Codesession safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Codesession?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Codesession free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Codesession?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Codesession by tomevault-io — Agent Skill

Name: Codesession
Author: tomevault-io

Codesession

Track AI agent session costs, tokens, file changes, and git commits. Use when starting tasks, logging AI usage, checking budgets, or ending sessions. The MCP server handles all operations automatically. Use when this capability is needed.

tomevault-io c14b906 2 files · 3.1 KB Updated Sep 17, 2026

File contents

codesession — Session Cost Tracking

You have access to codesession MCP tools for tracking AI session costs. Use them throughout your workflow.

When to Use

Task start: Call start_session with a descriptive name
After AI calls: Call log_ai_usage with provider, model, and token counts
Budget checks: Call check_budget before expensive operations
Add context: Call add_note for milestones and progress
Task end: Call end_session with completion notes

MCP Tools Available

Tool	Purpose
`session_status`	Get active session status (cost, tokens, duration)
`start_session`	Start a new tracking session
`end_session`	End session and get full summary
`log_ai_usage`	Log token usage (auto-prices 21+ models incl. Codex)
`add_note`	Add timestamped notes
`get_stats`	Overall statistics across all sessions
`list_sessions`	List recent sessions
`check_budget`	Check spending breakdown by model

Auto-Pricing

Cost is auto-calculated for known models. Supported providers: anthropic, openai, google, mistral, deepseek. Codex models supported: codex-mini-latest, gpt-5.1-codex-max, gpt-5.1-codex-mini, gpt-5.3-codex. If a model is unknown, provide the cost parameter manually.

Budget Awareness

Check check_budget before expensive operations
Warn the user if session cost exceeds $5.00
Suggest cheaper models if costs are escalating

Dashboard

Users can view all session data in a web dashboard:

npx codesession-cli dashboard

Proxy Mode & cs run (v2.5.0)

For zero-config tracking, users can either:

cs run <command> — one command that starts a session, starts the proxy, runs the command, and shows a cost summary on exit. No separate terminals needed.
cs proxy [--session name] — start the proxy and set ANTHROPIC_BASE_URL / OPENAI_BASE_URL to http://127.0.0.1:3739. All API calls are auto-tracked.

The proxy binds to 127.0.0.1 only and never stores prompt text or API keys.

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: codesessiondescription: Track AI agent session costs, tokens, file changes, and git commits. Use when starting tasks, logging AI usage, checking budgets, or ending sessions. The MCP server handles all operations automatically. Use when this capability is needed.---# codesession — Session Cost TrackingYou have access to codesession MCP tools for tracking AI session costs. Use them throughout your workflow.## When to Use- **Task start**: Call `start_session` with a descriptive name- **After AI calls**: Call `log_ai_usage` with provider, model, and token counts- **Budget checks**: Call `check_budget` before expensive operations- **Add context**: Call `add_note` for milestones and progress- **Task end**: Call `end_session` with completion notes## MCP Tools Available| Tool | Purpose ||------|---------|| `session_status` | Get active session status (cost, tokens, duration) || `start_session` | Start a new tracking session || `end_session` | End session and get full summary || `log_ai_usage` | Log token usage (auto-prices 21+ models incl. Codex) || `add_note` | Add timestamped notes || `get_stats` | Overall statistics across all sessions || `list_sessions` | List recent sessions || `check_budget` | Check spending breakdown by model |## Auto-PricingCost is auto-calculated for known models. Supported providers: `anthropic`, `openai`, `google`, `mistral`, `deepseek`. Codex models supported: `codex-mini-latest`, `gpt-5.1-codex-max`, `gpt-5.1-codex-mini`, `gpt-5.3-codex`. If a model is unknown, provide the `cost` parameter manually.## Budget Awareness- Check `check_budget` before expensive operations- Warn the user if session cost exceeds $5.00- Suggest cheaper models if costs are escalating## DashboardUsers can view all session data in a web dashboard:```bashnpx codesession-cli dashboard```## Proxy Mode & cs run (v2.5.0)For zero-config tracking, users can either:1. **`cs run <command>`** — one command that starts a session, starts the proxy, runs the command, and shows a cost summary on exit. No separate terminals needed.2. **`cs proxy [--session name]`** — start the proxy and set `ANTHROPIC_BASE_URL` / `OPENAI_BASE_URL` to `http://127.0.0.1:3739`. All API calls are auto-tracked.The proxy binds to `127.0.0.1` only and never stores prompt text or API keys.---> Converted and distributed by [TomeVault](https://tomevault.io/claim/brian-mwirigi) — claim your Tome and manage your conversions.

Frequently asked questions