Agent Cost Report
A Claude-Mem skill that produces a cost and failure report on a user's coding-agent work, by default for the last seven full days.
What the skill teaches
A Claude-Mem skill that produces a cost and failure report on a user's coding-agent work, by default for the last seven full days. A bundled Python script reads token usage from local Claude Code and Codex transcripts, prices it at OpenRouter's public list prices fetched at run time (so dollar figures are labelled estimated), and uses Claude-Mem's memory search to label work items and cite evidence. The report asks what was finished, what each outcome cost, what was wasted on loops, rework or wrong turns, and whether unapproved actions were attempted. Output is an HTML report, an optional PDF from headless Chrome, and JSON and CSV files. Optional sources such as an OpenRouter key need the owner's approval each time.
Capabilities
- Total token use from Claude Code and Codex transcripts
- Estimate cost per completed piece of work
- Classify wasted effort such as looping and rework
- Write HTML, PDF, JSON and CSV reports
About
- Publisher
- thedotmack
- Tool
- Data analysis
Works with
Install
- Run this to add it to Any client:
npx claude-mem install
What's inside
- .gitignore
- CHECKSUMS.txt
- scripts/acr.py
- scripts/acr/__init__.py
- scripts/acr/behavior.py
- scripts/acr/classify.py
- scripts/acr/costs.py
- scripts/acr/devices.py
- scripts/acr/evidence.py
- scripts/acr/labels.py
- scripts/acr/measure.py
- scripts/acr/mistakes.py
- scripts/acr/owner.py
- scripts/acr/patterns.py
- scripts/acr/period.py
- scripts/acr/prices.py
- scripts/acr/render.py
- scripts/acr/rollup.py
- scripts/acr/rules.json
- scripts/acr/rules.py
- scripts/acr/sample.py
- scripts/acr/snapshot.py
- scripts/acr/sync.py
- scripts/acr/transcripts.py
- scripts/acr/wins.py
MCP servers and skills can run code on your computer and act on your data. Review the source before installing.
This skill includes scripts that your agent may run.
Details
| Fact | Value | Source |
|---|---|---|
| Type | Skill | |
| Tool | Data analysis | |
| Publisher | thedotmack | source |
| Official status | Not stated in its documentation | |
| Needs an API key or sign-in | Not stated in its documentation | |
| Includes scripts | Yes | source |
| Platforms | Not stated in its documentation | |
| AI clients | Claude Code | source |
| Licence | Apache-2.0 | source |
| Pricing | Not stated in its documentation | |
| Activity | Last commit Nov 18, 2026118,035 GitHub starsDownload data not available (not on npm or PyPI) | source |
| Links | Repository Website |
More from thedotmack
27 skills
- claude-mem-install (Skill)
- claude-mem-install (Skill)
- openclaw (Skill)
- community-sweep (Skill)
- babysit (Skill)
- mode-creator (Skill)
Also listed under: Data analysis
Sources
- GitHub repositorygithub.com/thedotmack/claude-mem · Backs: AI clients, Licence, Publisher, ActivityNov 18, 2026
- Skill file (SKILL.md)github.com/thedotmack/claude-mem · Backs: Includes scriptsNov 15, 2026
- Skill file (SKILL.md)github.com/thedotmack/claude-memNov 18, 2026
- Folder in the repository (agent-cost-report)github.com/thedotmack/claude-mem · Backs: Includes scriptsNov 18, 2026