agentrigs
+ submit rig
~ / rigs / silouone / clens

silouone/clens

Claude Code session capture and analysis. Trace tool calls, detect backtracks, analyze decisions, track edit chains, and measure plan drift. Local-first, zero-dependency observability.

↗ GitHub ★ 4 mit updated 3mo ago project Claude Code Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~165 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/silouone/clens

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit <redacted>-analysis .claude/skills/backtrack-analysis
$ npx degit <redacted>-report .claude/skills/journey-report
$ npx degit <redacted>-analysis .claude/skills/session-analysis
$ npx degit <redacted>-compare .claude/skills/session-compare
$ npx degit <redacted>-report .claude/skills/session-report

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (5)

backtrack-analysisjourney-reportsession-analysissession-comparesession-report

Similar rigs

edobreque/clens
Capture and analyze Claude Code sessions locally to track every tool call, decision, and reasoning step without external dependencies.
★ 2 project Claude Code 5 skills today
Pragmatist 165 tok ·
Gorrpo/claude-dotfiles
"Minha configuração centralizada do Claude Code - skills, plugins e configurações"
★ 0 setup Claude Code 2 mcp 24 skills 4mo ago
Skill Collector 7.4k tok ·
w0rp/claude-code-config
My Claude Code Configuration
★ 1 setup Claude Code 2 mcp 25 skills 5mo ago
Skill Collector 7.0k tok ·
fuxicodex/Fuxi
FuXi is a fast, self-contained AI coding agent that lives in your terminal — edit code, run commands, and drive tools, with cost-aware routing across LLM providers.
★ 3,353 project Claude Code 3 mcp 27 skills 1mo ago
Skill Collector 8.2k tok ·
copied ✓