A code-review tool that examines how tokens were spent during the current coding session. Tokens are the text units used by an AI assistant and can affect cost and response limits.

Use it to identify waste in a session and get concrete suggestions for reducing token use next time.

It shows where unnecessary reading, repeated research, vague requests, or other avoidable work used tokens.

cost-audit — Skill for Claude Code by berkcangumusisik

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add berkcangumusisik/claude-code-practices --skill cost-audit

Clone the repo

git clone --depth 1 https://github.com/berkcangumusisik/claude-code-practices

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/berkcangumusisik/claude-code-practices/cost-audit/github.svg)](https://agentmods.dev/skills/berkcangumusisik/claude-code-practices/cost-audit)

Your own site

<a href="https://agentmods.dev/skills/berkcangumusisik/claude-code-practices/cost-audit"><img src="https://agentmods.dev/badge/skills/berkcangumusisik/claude-code-practices/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/berkcangumusisik/claude-code-practices/cost-audit"><img src="https://agentmods.dev/badge/skills/berkcangumusisik/claude-code-practices/cost-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 645 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.

Model	Per session	Once invoked
Fable 5.1	$0.00025	$0.00645
Opus 5.5	$0.00010	$0.00258
Sonnet 5.5	$0.00005	$0.00129
Haiku 4.5	$0.00003	$0.00064

Measured 2mo ago against content hash c7c793709b18, 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.

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.

skills/cost-audit/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal

Make it visible where the tokens in this session actually went. Not guesses — evidence. Output: "do these 3 things next time and you save ~X%."

Step 1 — Capture current cost

/cost

Note the output: total tokens, input/output split, cache hit rate, total $.

Step 2 — Find the leaks

Scan the transcript for these signals:

Signal	How to detect it	Why it wastes tokens
Unnecessary file reads	`Read` calls touching `node_modules/`, `dist/`, `*.lock`, `coverage/`	Missing `.claudeignore`
Re-reading the same file	Same path appears in multiple `Read` calls	Context lost — `/compact` should have happened earlier
Reading entire large files	`Read` without `limit` on files >500 lines	Should have used `offset`/`limit` or `Grep`
Bash + grep/cat/find	`Bash` calls to `grep`, `cat`, `find`, `ls -R`	Dedicated tools (`Grep`/`Glob`/`Read`) are cheaper and more precise
Vague prompt → many tool calls	Single-word asks ("improve", "fix", "look") followed by 5+ tool calls	Prompt wasn't specific
Repeated onboarding research	Same concept re-discovered across sessions	Belongs in `CLAUDE.md`

Step 3 — Report

Give the user a report in this shape:

## Session summary
- Total: <tokens> (<$>)
- Cache hit: <%>

## Top 3 leaks
1. [Evidence]: X files under src/components/ were read in full; ~Y tokens combined
   Fix: add to .claudeignore → <lines>
   Estimated savings: ~Z%

2. ...

3. ...

## Action list
- [ ] Create .claudeignore with <lines>
- [ ] Add a "<topic>" section to CLAUDE.md
- [ ] Use `/compact <hint>` earlier in long sessions

Step 4 — Optional auto-fixes

If the user approves:

Create .claudeignore if missing, add the detected paths
Create a CLAUDE.md scaffold if missing, seed it with the repeated-research topics
Suggest a specific /compact hint phrase for this project

Rules

No guessing — only report what's in the transcript
Always a number — not "a lot", but "12,400 tokens"
Action-oriented — every finding ends with a concrete command or edit
Keep it short — 3 top leaks is plenty; skip the long tail

Read the full file on GitHub · 71 lines

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.

2mo ago First seen · 71 lines · 25 tokens per session scan A c7c793709b18

Subscribe to this mod's changes

cost-audit is a skill published in the GitHub repository berkcangumusisik/claude-code-practices (11 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 645 once invoked, about $0.0001 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 metrics Claude Code LLM ai-tools cheetsheet claude-ai developer-productivity

cost-audit next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cost-auditberkcangumusisik/claude-code-practices	Skill	11	6mo ago	MIT	A	25	Claude Code
open-sourcebrowser-use/browser-use	Skill	120k	yesterday	MIT	A	137	Claude Code
prompt-masternidhinjs/prompt-master	Skill	16k	15d ago	MIT	B	78	Claude Code, Codex
skill-builderyusufkaraaslan/Skill_Seekers	Skill	15k	1mo ago	MIT	A	38	Claude Code, Codex
pre-meeting-briefchrisblattman/claudeblattman	Skill	476	yesterday	MIT	A	23	Claude Code
schedule-querychrisblattman/claudeblattman	Skill	476	yesterday	MIT	A	17	Claude Code
todo-addchrisblattman/claudeblattman	Skill	476	yesterday	MIT	A	18	Claude Code, Codex