Burnlens Fix — Development skill for Claude Code
Find fixes that cut your Claude Code token usage, apply the ones you pick, and track what they save.
How to install Burnlens Fix
Installs to ~/.claude/skills/abhayjain33-burnlens-burnlens-fix/SKILL.md
mkdir -p ~/.claude/skills/abhayjain33-burnlens-burnlens-fix && curl -fsSL https://raw.githubusercontent.com/abhayjain33/burnlens/HEAD/commands/burnlens-fix.md -o ~/.claude/skills/abhayjain33-burnlens-burnlens-fix/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Burnlens Fix does
description: Find fixes that cut your Claude Code token usage, apply the ones you pick, and track what they save argument-hint: "[--days N] [--demo]" allowed-tools: Bash(bash:*), Read, Glob
burnlens recommendations (JSON list):
!`bash "${CLAUDE_PLUGIN_ROOT}/scripts/burnlens.sh" fixes --json $ARGUMENTS`
Work through these with the user:
- If the arguments include
--demo, these are example recommendations for synthetic data: show them as in step 2, say they're examples, and don't ap
Alternatives in Development
- Doctor — Environment diagnostics with interactive fixes — providers, auth, RTK, hooks, token optimization 2.8k ★
- Overnight PRs — Autonomous overnight loop — verify issues against the codebase, close stale ones, ship PRs through /ship (bug 324 ★
- Dashclaw Quality — Recurring find-and-fix quality pass over the whole DashClaw app — browser smoke (frontend-verify) + code gates 297 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Burnlens Savings
Show what the fixes you applied with /burnlens-fix have actually saved
Trim Context
Find and fix sources of Claude Code "token bloat" in a repo — oversized CLAUDE.md (vs the 40k-char limit), blo
Tokmira
Free, local-first Claude Code & Codex usage monitor. Track quotas, analyze token usage, and find waste.
Burnlens
Open your burnlens token-usage dashboard and summarize where your tokens went
Buzz
Profile Lean declarations, find the slow ones, trace-diagnose the root cause, and fix them until each elaborat
Cpv Batch Scope Fix
Apply fixes for scope-aware doctor findings across a fleet of project folders. One cpv-doctor-agent per projec
Related Agents
AI Cost Optimizer
Audits an LLM application or AI agent for token cost and rate-limit risk, using its usage logs and code, and r
Performance Monitor
Monitor agent execution, track token usage, measure response quality, and optimize workflows
Light Review Step3
Stage 3 of the Delphi review pipeline — verify code fixes hold up, revert the ones that don't, then compile. F