agentmods.dev

cost-audit

cost-audit is a skill for Claude Code from ChewbaccaRoars/claude-code-cost-tracker. It costs 69 tokens per session (425 once invoked), scanned A, original, MIT.

A context-cost audit that examines installed skills, connections, plugins, hooks, memory files, permissions, and recorded usage to find what is taking up context space.

In plain words
What is it for?
Use it to audit your setup, investigate context or MCP bloat, compare usage over a selected period, and prioritize what to keep, reduce, or remove.
Why use it?
It helps explain why sessions are expensive or overloaded, and identifies unused or oversized setup components. It leaves decisions about disabling or reducing them to you.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the cost-tracker plugin — 6 skills, 3 hooks shipped together

not rated 6repo 4mo ago A scan 69 tokens original MIT

Good fit Use it to audit your setup, investigate context or MCP bloat, compare usage over a selected period, and prioritize what to keep, reduce, or remove.

Compare 6 skills from other repositories ↓
View source ↗ ChewbaccaRoars/claude-code-cost-tracker
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ChewbaccaRoars/claude-code-cost-tracker
Claude Code
/plugin install cost-tracker

Made for: Claude Code.

Or install cost-tracker, the plugin that ships this one along with the rest of its 6 skills, 3 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cost-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/chewbaccaroars/claude-code-cost-tracker/cost-audit/github.svg)](https://agentmods.dev/skills/chewbaccaroars/claude-code-cost-tracker/cost-audit)
Your own site
<a href="https://agentmods.dev/skills/chewbaccaroars/claude-code-cost-tracker/cost-audit"><img src="https://agentmods.dev/badge/skills/chewbaccaroars/claude-code-cost-tracker/cost-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cost-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/chewbaccaroars/claude-code-cost-tracker/cost-audit"><img src="https://agentmods.dev/badge/skills/chewbaccaroars/claude-code-cost-tracker/cost-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 425 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.00425
Opus 5.5 $0.00028 $0.00170
Sonnet 5.5 $0.00014 $0.00085
Haiku 4.5 $0.00007 $0.00042

Measured 2mo ago against content hash 1bb8e0f66ec8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cost-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/audit.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/cost-tracker/skills/cost-audit/SKILL.md · 44 lines

What it actually says

Context Audit - Find and Fix Context Bloat

You are a context cost analyst. The user wants to know what's inflating their context window and costing them money.

How It Works

The auditor scans the user's installed skills, MCP servers, plugins, hooks, memory files, and permissions. It estimates the token cost of each, correlates against actual usage from ~/.claude/cost-tracker/cost-log.jsonl, and produces a prioritized waste report.

Running the Audit

node "${CLAUDE_PLUGIN_ROOT}/skills/cost-audit/scripts/audit.js" $ARGUMENTS

Available arguments: today, week, month, all (default: month)

Instructions

  1. Run the audit script with the user's requested time range
  2. Present the output directly - it produces markdown tables sorted by monthly waste
  3. For follow-up questions, explain what each finding means and how to act on it
  4. "disable" means the user should remove the skill or disconnect the MCP
  5. "reduce" means the skill is used but oversized - suggest trimming the SKILL.md
  6. Never auto-disable anything - always let the user decide

Verdict Meanings

  • KEEP: Used in >10% of sessions or used in last 7 days
  • REDUCE: Used occasionally but the SKILL.md is >10KB - could be trimmed
  • DISABLE: Not used in 30+ days, costing money for no value
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 44 lines · 69 tokens per session scan A 1bb8e0f66ec8

Subscribe to this mod's changes

cost-audit is a skill published in the GitHub repository ChewbaccaRoars/claude-code-cost-tracker (6 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 425 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Analytics and metricsBuilding agents
Related

cost-audit compared with skills from other repositories

cost-audit next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cost-auditChewbaccaRoars/claude-code-cost-trackerSkill64mo agoMITA69Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code