parsifal1986/tokensburned/connect
Claude Code and agent skill by parsifal1986/tokensburned
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Connect a GitHub account to TokensBurned. Use for first-time setup, device authorization, or reconnecting; do not use for history-only imports or viewing existing totals.
Install
npx vskill@latest install parsifal1986/tokensburned/connectSKILL.md
Connect TokensBurned
Resolve the plugin root from this skill's location and use node <plugin-root>/bin/burn.js connect.
- Run connection only after the user asks to connect, install, or set up the service.
- Explain that GitHub authorization verifies identity and that one TokensBurned device credential is stored in
~/.burn/credentials.jsonwith user-only permissions. - Open the server-provided complete verification URL when available so the short code is filled automatically. The user must still verify the displayed code and device name, then explicitly confirm before GitHub authorization. Use the printed short code only as a manual fallback, and never ask them to use a code supplied by someone else.
- Account privacy is stored by the service for the verified GitHub account and inherited on every connected device. Connecting must never reset or reprompt for an existing policy; new accounts start private. Pass
--publish-cardonly when the user explicitly asks to change the account to public and acknowledges that totals, harness/provider/model breakdowns, activity heatmaps, rank, and GitHub identity become public. - Treat history import as separate consent. Pass
--backfill --harness codexin Codex or--backfill --harness claude-codein Claude Code only when the user explicitly asks to import existing history; otherwise pass--no-backfillso a non-interactive harness never imports by implication. - Pass
--all-harnessesonly when the user explicitly asks to import every recognized harness and acknowledges the expanded local file scope. - When history import is approved, state that only aggregate token and request counts, tool/provider/model labels, and activity dates and hours are uploaded; session identifiers stay local. Prompts, replies, tool payloads, source code, repository paths, and transcript files are not uploaded.
- Start background collection with
tokensburned runonly when the user requests it. Do not add proxies or Git synchronization.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/connect/SKILL.md
Popularity
- Repository stars
- 87
- Repository forks
- 6
- 7-day trend score
- 22
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/parsifal1986/tokensburned/connect)