Clens — Development skill for Claude Code
Claude Code session capture and analysis.
How to install Clens
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open silouone/clens and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Clens does
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.
Alternatives in Development
- Skill Creator — Create new skills, modify existing skills, and measure skill performance 94.1k ★
- Om Dump — Freeform capture mode 4.6k ★
- Fidelity — Measure how faithfully a clone reproduces a site — pixel-diff plus motion-fidelity into one 0-100 score, a let 3.6k ★
README
cLens — Session Observability for Claude Code
[](https://www.npmjs.com/package/@silou/clens) [](LICENSE) [](https://github.com/silouone/clens/actions/workflows/ci.yml)
**Local-first session capture and analysis for Claude Code agents.** See what your agent actually did — every tool call, backtrack, decision, and reasoning step — then explore it all in a browser dashboard. Zero network, zero server, zero telemetry.
30-second quickstart
npm install -g @silou/clens # or: bun install -g @silou/clens

clens init # 1. install hooks into this project
# ... use Claude Code normally ...
clens distill --last # 2. analyze your latest session
clens web # 3. open the dashboard in your browser
That's it. `clens init` wires the capture hooks, your sessions land as local JSONL, and `clens web` launches the full dashboard at `http://127.0.0.1:3700`. Prefer the terminal? `clens explore` opens the interactive TUI instead.
Web Dashboard
`clens web` serves a browser dashboard for everything cLens captures — session list, per-session detail, multi-agent trees, decision and backtrack timelines, edit chains, plan drift, and cross-session insights. The web server is bundled into the CLI binary at build time, so npm consumers need nothing extra to run it.

clens web # launch on http://127.0.0.1:3700, opens your browser
clens web --port 8080 # custom port
clens web --no-open # don't auto-open the browser
clens web --global # aggregate sessions across all your repos
The dashboard is served locally and gated behind a per-launch token printed to your
Related Skills
Pbi Optimise
Run a 14-rule performance scan on any DAX measure, identifying anti-patterns like unnecessary iterators, FILTE
Governance Review Agent
Chains adoption-report, drift detection scoped to at-risk teams, and stakeholder-brief into a periodic governa
Perfetto Android Skills
Agent skill: measure, diagnose, fix and re-measure Android app performance from a Perfetto trace
Trace Triage
Root-cause a failed or slow agent run by walking its trace on the Progress Observability Platform.
Editscore Ladder Run
Run an EditScore-7B pairwise ladder for an image-edit generator (SDEdit / diffusion / LoRA / distilled step-co
Goal Check
Check whether recent tool activity still relates to the stated goal in task_plan.md, reporting a drift score a
Related Agents
Deep QA
Use this agent as a proactive quality sentinel — dispatched after implementation work to audit code quality, d
Performance Monitor
Monitor agent execution, track token usage, measure response quality, and optimize workflows
Size Check
Build the vlist library and measure gzipped bundle sizes per feature. Use after code changes to detect size re