Query AgentlensPro token/cost forensics from any project via the single global agentlenspro executable — use when a session is burning tokens, a rate-limit window drains too fast, the prompt cache keeps breaking, you need the cost of a session / heartbeat /…
Emasoft/AgentlensPro
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 5
- GitHub stars
- 3
- GitHub forks
- 0
Install with an AI assistant
Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/Emasoft/AgentlensPro.Loading the repository README…
Skills in this repository
Showing 5 of 5 collected skills.
Scan a codebase for errors and fix them with a token-calibrated agent fleet. Covers the DYNAMIC half that linters cannot see — failing tests, CI failures, flakes — with a flake gate that classifies before diagnosing, signature clustering so one root cause is…
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Measure what a Claude Code agent actually puts in its context window, and what its SECOND turn costs — by spawning it for real and reading the raw API captures, not by guessing from its definition. Load this when someone asks how a new or custom agent…
Keep images and bulk tool output from quietly dominating a session's token cost. Load this BEFORE reading screenshots, renders, diagrams, or PDFs for visual QA in a conversation that already has real history; before a long agentic loop that will look at…