A personal Claude Code impact report for justifying your usage to a manager or a self-review: what you shipped, which projects it went to, and each project's share of your usage. Reads your ~/.claude/projects transcripts and runs read-only git locally; only counts and project names are sent to write it up, and the report stays on your machine.
- Stars
- 47,602
- Version
- v1
- Copies
- 0
Overview
Waxell rates it high risk: 6 findings, highest severity high.
- Highest severity
- high
- Findings
- 6
- What ran
- Static analysis + deep scan
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
Skills in this plugin
We don't republish the plugin's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked 2 days ago
Result
High risk Waxell rates it high risk: 6 findings, highest severity high.
Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work
Findings (6)
high · 4
- high
YARA Match: YARA rule 'agent_skill_prompt_injection_hidden_instructions': Prompt injection or hidden instructions embedd
skills/receipts/SKILL.md:14 · skillspector:YR4
- high
YARA Match: YARA rule 'agent_skill_prompt_injection_hidden_instructions': Prompt injection or hidden instructions embedd
skills/receipts/scripts/mine-transcripts.mjs:121 · skillspector:YR4
- high
Prompt Injection: Instruction Override
skills/receipts/SKILL.md:142 · skillspector:P1
- high
Prompt Injection: Instruction Override
skills/receipts/scripts/mine-transcripts.mjs:347 · skillspector:P1
medium · 1
- medium
Tool Misuse: Unsafe Defaults
skills/receipts/scripts/mine-transcripts.mjs:1098 · skillspector:TM3
info · 1
- info
assets/sample-receipt.png: PNG image
assets/sample-receipt.png · binary_risk:B6
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
One version so far: v1, seen 2026-11-16.
Files
Files
7 files, 363 KB in total. Names only; open them on GitHub.
- .claude-plugin/plugin.json
- LICENSE
- README.md
- assets/make-sample.mjs
- assets/sample-receipt.png
- skills/receipts/SKILL.md
- skills/receipts/scripts/mine-transcripts.mjs
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More engineering skills and plugins
receiptsAnthropicGenerate a personal Claude Code usage & impact report ("receipts") from this machine's local session transcripts, for justifying Claude… No issuesEngineeringAI & agents48k
swift-lspAnthropicSwift language server (SourceKit-LSP) for code intelligence No issuesEngineeringAI & agents48k
typescript-lspAnthropicTypeScript/JavaScript language server for enhanced code intelligence Review findingsEngineeringAI & agents48k
agentic-workflowsGitHubRoute gh-aw workflow design/create/debug/upgrade requests to the right prompts. No issuesEngineeringProductivity41k