kmshihab7878/claude-code-setup/session-bootstrap

Claude Code and agent skill by kmshihab7878/claude-code-setup

Trust tier 2
  • community
LLM review pending
Source check pending

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

Confirm the evolution layer is active at session start and report what was injected. Use at the start of any session where behavior may have recently changed, or when the user asks what guidance is active. Read-only — does not modify stable/.

Install

npx vskill@latest install kmshihab7878/claude-code-setup/session-bootstrap

SKILL.md

session-bootstrap

When to use

  • The user asks "what's loaded?" or "what rules apply?"
  • A new session just started and you want to confirm the evolution contract landed.
  • Troubleshooting why Claude is/isn't following a stable learning.

What to do

  1. Run: bash ~/.claude/evolution/bin/evolve-status.sh
  2. Show the user:
  • kill-switch state
  • number of stable learnings in effect (grep ^- in ~/.claude/evolution/stable/global.md)
  • any project-scoped stable file matching basename $(pwd)
  • last 3 session records
  1. If the hook didn't fire (no recent sessions.jsonl record), flag it and suggest checking settings.json for the SessionStart hook.

What NOT to do

  • Do not read raw records (corrections.jsonl, outcomes.jsonl) and treat them as operating rules. Those are evidence, not stable guidance.
  • Do not edit stable/global.md or any file under ~/.claude/evolution/stable/. Changes go through /evolution promote.
  • Do not bloat the output. The dashboard is terse on purpose.

Inputs / outputs

  • Inputs: none (reads ~/.claude/evolution/ state).
  • Outputs: text dashboard to the user.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

See the full security report

Quality evaluation

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

See evaluation results

Source

Popularity

Repository stars
6
Repository forks
1
7-day trend score
10

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/kmshihab7878/claude-code-setup/session-bootstrap/badge)](https://verified-skill.com/skills/kmshihab7878/claude-code-setup/session-bootstrap)

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