Babysit
Watch a pull request or review cycle until it is ready to merge. Use when asked to babysit, monitor, or keep checking PR comments, reviews, and CI until all actionable issues are…
Coding Workflow
claude-mem113k
Believable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.
Install
This skill is part of the claude-mem plugin and uses its shared scripts and agents. Install the whole plugin by typing these in Claude Code:
> /plugin marketplace add thedotmack/claude-mem> /plugin install claude-mem@thedotmackThe first command adds the publisher's marketplace, the second installs the plugin. Start a new session if the skills don't show up straight away.
How to use Agent Cost Report
Once it's installed, Claude reads this skill on its own whenever a request matches what it's for, so you don't have to mention it by name.
It includes scripts that Claude may run on your computer, so skim them on GitHub before you install. It is part of the claude-mem plugin and uses that plugin's shared scripts and agents, so install the whole plugin for the best results.
What the instructions cover
- 1Purpose
- 2Insight north star
- 3Questions the report must answer
- 4When to use
- 5Default scope (ALWAYS)
- 6Progressive Mem Search (ALWAYS)
- 7Work categories (ALWAYS)
- 8Failure / waste types (ALWAYS)
- 9Cost model
- 10Behavior metrics (heuristic until reviewed)
- 11Money labeling (ALWAYS)
- 12Line-item schema
Section headings from the skill's SKILL.md file.
What's inside · 54 files
- .gitignore
- CHECKSUMS.txt
- SKILL.md
- VERIFICATION.md
- 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/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
- scripts/tests/_db.py
- scripts/tests/_paths.py
- scripts/tests/fixtures/codex/sessions/2026/09/18/rollout-codex-1.jsonl
- scripts/tests/fixtures/make_report_fixtures.py
- scripts/tests/fixtures/prices_sample.json
- scripts/tests/fixtures/projects/-workspace-proj-a/sess-aaaa.jsonl
- scripts/tests/fixtures/projects/-workspace-proj-b/sess-bbbb.jsonl
- scripts/tests/fixtures/report-1day.json
- scripts/tests/fixtures/report-30day.json
- scripts/tests/fixtures/report-7day.json
- scripts/tests/fixtures/report-empty.json
- scripts/tests/fixtures/report-session.json
- scripts/tests/test_behavior.py
- scripts/tests/test_devices.py
- + 14 more files on GitHub →
More from claude-mem
See all →Backup Setup
Set up, check, or restore local claude-mem database snapshots. Use when the user says "set up backups", "back up my memories", "backup status", or "restore my database".
Coding Workflowclaude-mem113k
More Claude skills for coding
See all →BrainstormingTop pick
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it…
Coding Workflow
Jesse Vincent312k
Systematic DebuggingTop pick
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Coding WorkflowJesse Vincent312k
CavemanTop pick
Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop…
Coding Workflow
Julius Brussee117k