Dead weight
Everything installed that hasn’t run in 30, 60 or 90 days, with the date it last did.
See which agents and skills earn their place.
RChursin_ reads your team’s coding-agent sessions and shows what each agent and skill costs, how often it runs, and whether it helps. Then it tells you what to keep, cut, merge or fix.
Reads sessions from
- Claude Code
- Cursor
- OpenCode
- Codex
Why this exists
“I had 12 agents and 80 skills. I used 3 agents and about 10 skills. I couldn’t tell which of the rest were dead weight, so I built RChursin_.”
- Agents built
- 12
- Agents used
- 3
- Skills built
- 80
- Skills used
- ~10
Product
Usage isn’t usefulness. See both.
Counting runs is the easy part. RChursin_ ties every agent and skill to what happened next: the task finished, the tests passed, the PR merged.
Usefulness score
Did sessions that used it finish more tasks, faster, for less?
Trigger check
Skills the agent never picks on its own. The description usually needs work.
Overlap finder
Two skills doing one job, with a suggested merge.
Context tax
What your descriptions add to every turn, before any work starts.
Cleanup PRs
Approve the report and get a pull request that removes, merges or rewrites what you don’t need. You review it like any other change.
Agent activity
Twelve agents. Three do the work.
This is what most setups look like once you can see them. RChursin_ shows it for your team, every day.
Sample dataEach square is one agent on one day, last 30 days. 3 of 12 agents ran at all.
No runsFewer to more runs
How it works
Set up in one shell profile.
- 1
Connect
Turn on your agent’s telemetry, or point us at your local session files. Prompts stay out by default.
- 2
Map
We match each session to the agent and skill files in your repo, and to the result: task done, tests passing, PR merged.
- 3
Act
A weekly report says what to keep, cut, merge or fix, with pull requests ready to review.
export CLAUDE_CODE_ENABLE_TELEMETRY=1export OTEL_LOG_TOOL_DETAILS=1 # real agent and skill namesexport OTEL_METRICS_EXPORTER=otlpexport OTEL_LOGS_EXPORTER=otlpexport OTEL_EXPORTER_OTLP_ENDPOINT=https://YOUR_ENDPOINTexport OTEL_EXPORTER_OTLP_HEADERS="Authorization=Bearer YOUR_TOKEN"FAQ
Questions engineers ask first.
Claude Code already shows usage. Why do I need this?
Built-in tools show one machine and the last few days. RChursin_ shows your whole team, keeps the history, and ties every agent and skill to results, not just to how often it ran.
Does my code or my prompts leave my machine?
The local scan runs on your machine and sends nothing. Team mode receives usage counts, costs and names. Claude Code keeps prompts out of its telemetry unless you turn them on.
How do you decide something is useful?
We compare sessions that used an agent or skill with similar sessions that didn’t: did the task finish, how long did it take, and what did it cost.
Which coding agents do you support?
[CONFIRM BEFORE LAUNCH] Claude Code first. Cursor, OpenCode and Codex next.
Why does an unused skill cost anything?
Its name and description are loaded on every turn so the agent knows it exists. That’s about 100 tokens a skill. Small alone, but 80 skills is around 8,000 tokens before any work starts.
Find your dead weight this week.
Connect one repo. Your first report is ready after a day of normal work.