Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Agent Cost Report

Turns Claude Code transcripts into a manager-readable HTML/PDF report of agent cost, waste, and shipped outcomes.

Data & AnalyticsAdvanced★ 94,740⑂ 8,379AI score 8/10Last updated: Sep 26, 2026

What it does

  • Parses ~/.claude/projects/**/*.jsonl transcripts, deduping assistant replies and summing input/output/cache tokens.
  • Prices them against OpenRouter public list rates to produce an ESTIMATED headline, reserving MEASURED for sanctioned provider data and EXTRAPOLATED for sessions with no local transcript.
  • Groups sessions into work items keyed to completed outcomes, tagging 6 work categories and 16 failure/waste types (looping, rework, unauthorized action, etc.).
  • Emits a self-contained report.html, plus report.pdf, report.json, line-items.csv, evidence.json, and labels.review.json for a label review pass.
  • Defaults to the last 7 full PT days excluding today; supports --session, --project, and explicit date ranges.

Who it's for

  • Team leads who must justify agent spend to management with labeled numbers.
  • Heavy Claude Code users already running the claude-mem / mem-search plugin.
  • Anyone asking "was this week of agent work actually worth it?"

Examples

  1. "Give me last week's agent cost report" → runs prices → collect → rollup → render for the default 7-day window.
  2. "What did this one session cost?" → --session <id> produces a single-session cost, waste and failure breakdown.
  3. "Summarize September spend for the claude-mem project" → --project claude-mem --start 2026-09-01 --end 2026-10-01 with merged-PR wins listed via read-only gh.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/thedotmack/claude-mem/HEAD/claude-mem-cursor/skills/agent-cost-report/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the claude-mem-cursor/skills/agent-cost-report folder from the GitHub repo thedotmack/claude-mem into my ~/.claude/skills/agent-cost-report/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/thedotmack/claude-mem.git && mkdir -p ~/.claude/skills && cp -r claude-mem/claude-mem-cursor/skills/agent-cost-report ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and move to a folder where you keep code.
  2. Clone the repo: git clone https://github.com/thedotmack/claude-mem.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill in: cp -r claude-mem/claude-mem-cursor/skills/agent-cost-report ~/.claude/skills/
  5. Verify Python with python3 --version (3.9+ required; no pip installs needed).
  6. For PDF output, install headless google-chrome; without it the run still produces canonical HTML.
  7. Restart Claude Code and ask for "an agent cost report".
  8. For the evidence review pass, also install the claude-mem plugin and its mem-search MCP server; optional measured spend needs an inference-only OPENROUTER_API_KEY in your environment.
View source on GitHub ↗License: Apache-2.0