token-usage-audit
/token-usage-audit
Audit where tokens are being wasted across startup context, shell output, repeated file reads, bloated agent docs, oversized summaries, and compaction loss. Use when token budget is tight, sessions are degrading, or an agent setup needs measurement-driven optimization.
- Author
- markoblogo ↗
- Repository
- abvx-agent-skills ↗
- Licence
- MIT
- Last repository change
- 14.10.2026
Assessment and security
- Files in this package
- 3
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 14.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Audit where tokens are being wasted across startup context, shell output, repeated file reads, bloated agent docs, oversized summaries, and compaction loss. Use when token budget is tight, sessions are degrading, or an agent setup needs measurement-driven optimization.
Original author description
Audit where tokens are being wasted across startup context, shell output, repeated file reads, bloated agent docs, oversized summaries, and compaction loss. Use when token budget is tight, sessions are degrading, or an agent setup needs measurement-driven optimization.
How it works
- Waste Categories
- Audit Workflow
- Practical Signals
- Deliverable
- Guardrails
SKILL.md preview
--- name: token-usage-audit description: Audit where tokens are being wasted across startup context, shell output, repeated file reads, bloated agent docs, oversized summaries, and compaction loss. Use when token budget is tight, sessions are degrading, or an agent setup needs measurement-driven optimization. license: MIT metadata: abvx_status: experimental abvx_origin: adapted --- # Token Usage Audit Save tokens by measuring the waste categories before optimizing them. ## Waste Categories Audit these in order: 1. startup-context weight; 2. shell and tool-output noise; 3. repeated file reads or re-analysis; 4. oversized handoffs and summaries; 5. stale skills, prompts, or always-loaded docs; 6. compaction loss and re-derivation cost. ## Audit Workflow 1. Identify the current failure mode: - output overflow; - startup bloat; - long-session decay; - repeated repo rediscovery. 2. Estimate which category dominates. 3. Apply the narrowest corrective skill: - `rtk-assisted-shell` or `shell-output-compaction`; - `graph-guided-code-reading`; - `token-efficient-execution`; - `lean-context-layout`; - `compaction-survival`; - `token-frugal-mode`. 4. Re-check after the intervention: - fewer broad reads; - shorter command output; - smaller startup docs; - cleaner resume state. 5. Record what changed so the same waste is not rediscovered next session. ## Practical Signals - top-level agent file is large and generic; - same README or module keeps getting reopened; - shell output dominates the conversation; - compaction causes “what were we doing?” recovery turns; - too many installed skills are irrelevant to current work; - long status updates cost more than the actual edit. ## Deliverable Report: - biggest waste category; - corrective skills used; - what was changed; - expected future savings. ## Guardrails - Do not chase precision that costs more tokens than it saves. - Do not instrument everything if a clear dominant waste category is already visible. - Optimize the highest recurring cost first, not the most novel one.
Files in this package (3)
- SKILL.md 2 KB
- SKILL_CARD.md 1 KB
- agents/openai.yaml 1 KB
Versions
The database has no other skills named token-usage-audit.
Database snapshot: 13.11.2026 · package version 380284ef842d (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90token-efficient-execution
Reduce token waste in long coding-agent sessions by avoiding repeated reads, noisy output, oversized context, broad rewrites, and unnecessary narration. Use on long tasks, heavy repos, multi-file audits, shell-heavy debugging loops, or whenever token budget is a practical delivery constraint. - 100tokenfisher
Report where Claude Code tokens go (by category, model, tool result, cache rebuilds, startup context) and how to cut them. Use when the user asks about token usage, cost, context size, or why usage is high. - 86token-audit
Read-only audit of what uses up tokens and usage in Claude Code for this project (memory files, MCP tools and deferral, model and effort, hooks, subagent models, scheduled work, the prompt cache). Use when the user says "token audit", "why am I running out of tokens", "why am I… - 100session-waste-report
Waste report for coding-agent sessions in Claude Code, Codex, Gemini CLI, and OpenCode: finds where tokens, money, and time were wasted, and the fix for each kind of waste. Use when the user asks where tokens or money went or why the bill is so high; about habits that burn… - 100token-audit
Use when the user asks where their tokens or usage go, why they hit limits so fast, or to slim their setup (CLAUDE.md, memory, skills, plugins). Measures with Anchor, then applies the fixes they approve. - 90context-budget
Reduce repeated reading and implementation work while preserving the requested result. Use for incremental research or RedBot saved-library updates, large tool output, repeated source/history reads, token costs, 省 token / 上下文消耗, and Ponytail reuse checks before implementation.