Calculate and display the token usage, turns, and estimated cost for the active session and subagent runs by parsing the harness session logs. Use when the user asks for token usage, session cost, or types `/pi-cost`.
Scanned 9/12/2026
Install to Claude Code
npx -y skills add gaia-research/gaia-skill-tree --skill pi-cost --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Pi Cost?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/gaia-research-pi-cost-gaia-skill-tree)More formats (shields.io, HTML) on the badges page.
---
name: pi-cost
description: >-
Calculate and display the token usage, turns, and estimated cost for the active session
and subagent runs by parsing the harness session logs. Use when the user asks for
token usage, session cost, or types `/pi-cost`.
version: 1.0.0
---
# pi-cost
A utility skill to parse and estimate costs for the active Pi coding agent session, including any subagents called during the run.
## Setup
The Python helper script is pre-installed in the skill folder:
`scripts/pi_cost.py`
No extra dependencies are required.
## Usage
When triggered, execute the helper script using the `bash` tool:
```bash
python3 .claude/skills/pi-cost/scripts/pi_cost.py
```
This will output:
1. Active session file name and path.
2. Main session stats: total turns, tokens (input/output/cacheRead/cacheWrite), and estimated cost based on standard model pricing.
3. Nested subagent runs: breakdown of subagent name, model, turns, token details, and estimated cost.
4. Total consolidated session summary.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling