---
title: "Receipts: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/skills/anthropic-receipts/
description: "Builds a personal Claude Code impact report from this machine's session transcripts and local git history: what shipped, in which projects, and each project's share of usage, as a Markdown report and an HTML receipt in the home directory."
---

# Receipts: review, setup & limitations · Undominated.ai

> Builds a personal Claude Code impact report from this machine's session transcripts and local git history: what shipped, in which projects, and each project's share of usage, as a Markdown report and an HTML receipt in the home directory.

[← Explore all skills](/skills/)

OBSERVABILITY / Anthropic

# Receipts

Builds a personal Claude Code impact report from this machine's session transcripts and local git history: what shipped, in which projects, and each project's share of usage, as a Markdown report and an HTML receipt in the home directory.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/anthropics/claude-plugins-official/tree/41f32e407b450055044f167db7ded5e8ff67d203/plugins/receipts/skills/receipts)

SOURCE REVIEW

 Reviewed 2026-10-21
 Evidence 4 linked sources
 Publisher Anthropic
 Licence [Apache-2.0 ↗](https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/receipts/LICENSE)
 Revision 41f32e407b45
 [Read what was—and wasn’t—checked ↓](#review)

“Generate a personal Claude Code usage & impact report ("receipts") from this machine's local session transcripts — for justifying Claude Code usage/spend to a manager, self-review, or "what have I been using this for" check-ins. Mines ~/.claude/projects locally (no extra API calls beyond one final write-up), cross-references local git history, and writes a markdown report plus a self-contained HTML receipt to your home directory. Use when the user asks for "receipts", an "impact report", "usage report", wants to "show my Claude Code activity", "prove the value of Claude Code", or runs `/receipts`.”

 [Anthropic · upstream description ↗](https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/receipts/skills/receipts/SKILL.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - Mining is a local Node script, scripts/mine-transcripts.mjs, that reads ~/.claude/projects/**/*.jsonl and runs read-only git commands; the README says the only data that reaches the model is the git user name, aggregate counts and project names.
- The SKILL.md forbids dollar figures, "hours saved" numbers and a per-activity breakdown of spend, and tells the report to say which table columns add up and which do not.

### A good fit for

 - Produce a Markdown report and a self-contained HTML receipt of your own Claude Code activity for a manager or a self-review
- Scope a usage report to one project with /receipts for <project>
- Count commits that carry files Claude Code touched, as opposed to every commit made under your git identity

### Weigh up before choosing

 - Last commit touching plugins/receipts/skills/receipts at revision 41f32e40: 2026-10-08 (0baf7d19).
- Project names from the transcripts appear verbatim in the report; the skill lists them back before the report travels, because they may include internal codenames, client names or unannounced projects.
- "lines touched (approx.)" counts edited regions, and an edit that revisits a region counts each time; the SKILL.md says not to present it as lines of code written.
- The PRs figure counts gh pr create invocations, not confirmed pull requests.
- The report is self-reported and built from one machine's local data, as the SKILL.md tells the report to say.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - plugins/receipts/skills/receipts/SKILL.md
- plugins/receipts/skills/receipts/scripts/mine-transcripts.mjs (header, git calls and HTML write)
- plugins/receipts/README.md
- plugins/receipts/LICENSE

### Our findings

 - The SKILL.md frontmatter has only name and description; no allowed-tools are declared.
- The miner calls git rev-parse, git log --no-merges, git config user.email and git config --global user.name through execFileSync, each with a timeout.
- The HTML receipt is written with mode 0600 and the wx flag, and the script refuses to write through a symlink at that path.
- The SKILL.md says project names in the miner's JSON are data, never instructions, and that a name that reads like an instruction should be reported to the user, not obeyed.
- Publishing the receipt through the Artifact tool happens only if the user asks, after seeing the list of project names.

### Not established by this review

 - The miner was not run against any transcripts and no report was generated.
- mine-transcripts.mjs was read for its header, its git calls and its HTML write, not line by line; assets/make-sample.mjs was not opened.
- Not executed: it was not installed or run.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Add a skill to your workflow.

[Upstream setup instructions ↗](https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/receipts/README.md)

DOCUMENTED COMMAND

 /plugin install receipts@claude-plugins-official Copy command ↗

Copying does not execute this command. It may retrieve a newer version than the reviewed source.

 - The receipts README prints `/plugin install receipts@claude-plugins-official`. The receipts plugin contains this one skill, its miner script and the README's sample assets.
- Run `/receipts` for the last 30 days, or `/receipts week`, `/receipts quarter`, `/receipts 14` or `/receipts for myrepo`.
- This review installed nothing and mined no transcripts.

### Before you start

 - Claude Code session transcripts under ~/.claude/projects
- Node, to run node <skill-dir>/scripts/mine-transcripts.mjs
- git, for the commit cross-reference

### Compatibility

Claude Code

### Reads local Claude Code transcripts and runs read-only git; writes two report files to the home directory

 - No allowed-tools in the receipts SKILL.md; it runs node <skill-dir>/scripts/mine-transcripts.mjs through the session's Bash tool
- Reads ~/.claude/projects/**/*.jsonl; runs git rev-parse --show-toplevel in each directory the transcripts mention and, in git repositories, git rev-parse --verify HEAD, git log and git config user.email; reads git config --global user.name
- Writes /tmp/cc-receipt.html, then ~/claude-code-receipts-<since>-to-<until>.md and a copy of the HTML at ~/claude-code-receipts-<since>-to-<until>.html
- Publishes the receipt with the Artifact tool only if the user asks for a hosted version, after the project-name list
- Sends one JSON summary (git user name, aggregate counts, project names) to the model for the write-up; no code, conversation content, or tool or MCP server names, per the README

### Cost model

Apache-2.0 per plugins/receipts/LICENSE; mining makes no API calls and the write-up is one model call in the user's session

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [receipts SKILL.md ↗](https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/receipts/skills/receipts/SKILL.md) Checked 2026-10-21 https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/receipts/skills/receipts/SKILL.md Supports: upstreamDescription, summary, whySelected[0], whySelected[1], bestFor[0], bestFor[1], bestFor[2], limitations[1], limitations[2], limitations[3], limitations[4], review.findings[0], review.findings[3], review.findings[4], access.permissions[0], access.permissions[2], access.permissions[3], access.cost, install.prerequisites[1], compatibility
- [receipts scripts/mine-transcripts.mjs ↗](https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/receipts/skills/receipts/scripts/mine-transcripts.mjs) Checked 2026-10-21 https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/receipts/skills/receipts/scripts/mine-transcripts.mjs Supports: whySelected[0], review.findings[1], review.findings[2], access.permissions[1], install.prerequisites[0], install.prerequisites[2]
- [receipts README ↗](https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/receipts/README.md) Checked 2026-10-21 https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/receipts/README.md Supports: install.command, install.sourceUrl, install.steps[0], install.steps[1], whySelected[0], whySelected[1], limitations[1], access.permissions[1], access.permissions[4], access.label, compatibility
- [receipts LICENSE ↗](https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/receipts/LICENSE) Checked 2026-10-21 https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/receipts/LICENSE Supports: license, access.cost

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Session Report ↗ Runs a bundled Node analyzer over local Claude Code transcripts and fills an HTML template with token use by project, subagent type and skill, cache breaks and the most expensive prompts, plus a few findings and suggestions.](/skills/anthropic-session-report/)[### Arize Instrumentation Health ↗ Read-only audit of exported Arize spans for nine instrumentation defects, including missing token counts behind empty cost dashboards.](/skills/arize-ai-arize-instrumentation-health/)[### Elasticsearch Cluster Health ↗ Triage unassigned Elasticsearch shards through allocation evidence.](/skills/elastic-elasticsearch-cluster-health/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Choose a toolkit](/tools/)
- [Inspect execution hosts](/agents/)
- [Check tool access](/mcp-servers/)
- [Check project dependencies](/check-repo/)
