daseinlabs/parsec/setup

Claude Code and agent skill by daseinlabs/parsec

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Activate parsec — write the Claude Code routing env (ANTHROPIC_BASE_URL → local proxy), install the savings status line, and start the proxy. Use when the user wants to set up parsec, enable curation, or re-run a failed first-time setup.

Install

npx vskill@latest install daseinlabs/parsec/setup

SKILL.md

Setup normally runs automatically on first session, so reaching for this skill usually means that run failed or the user undid it with parsec disable. Run:

${CLAUDE_PLUGIN_ROOT}/bin/parsec setup

(No --auto flag — that is the hook-spawned first-run mode which respects terminal states; a manual run should retry.) Show the user the command's output and explain what happened based on which line it printed:

  • "routing written to Claude Code settings (127.0.0.1:PORT)" — setup added

ANTHROPIC_BASE_URL to the env block of ~/.claude/settings.json and started the proxy on that port. Tell the user to restart their Claude Code sessions: routing env is read at session launch, so this session and any other open ones are still talking straight to Anthropic. Undo anytime with parsec disable.

  • "routing NOT written: ANTHROPIC_BASE_URL is already …" — the user has

their own base URL set and parsec will never overwrite it. Relay the printed URL and the port; if they want curation they must point that variable at http://127.0.0.1:PORT themselves (or clear it and re-run setup).

  • "routing already pointed at a local parsec proxy — kept as-is" — setup

was already done; nothing changed. If their concern is a dead proxy rather than routing, that is /parsec:proxy, not setup.

  • "proxy pre-warm failed …" — routing is written but the proxy did not

start. Not fatal (the SessionStart hook retries next session), but you can fix it now by running ${CLAUDE_PLUGIN_ROOT}/bin/parsec up and reporting the result.

Setup is additive-only and idempotent: it never overwrites an env key or statusLine/subagentStatusLine the user authored themselves — it only writes absent keys and repoints entries it wrote under an older plugin version. Safe to re-run.

If the user has a dashboard API key to connect afterwards, that is /parsec:login, not part of setup.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
82
Repository forks
39
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
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/daseinlabs/parsec/setup/badge)](https://verified-skill.com/skills/daseinlabs/parsec/setup)

Something wrong with this skill or its page? Tell us.