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.
npx skills add berkcangumusisik/claude-code-practices --skill cost-auditgit clone --depth 1 https://github.com/berkcangumusisik/claude-code-practicesWrote 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.
[](https://agentmods.dev/skills/berkcangumusisik/claude-code-practices/cost-audit)<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.
<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>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 | $0.00013 | $0.00322 |
| Sonnet 5 | $0.00005 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00064 |
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 9d 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.
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
.claudeignoreif missing, add the detected paths - Create a
CLAUDE.mdscaffold if missing, seed it with the repeated-research topics - Suggest a specific
/compacthint 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
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.
- 9d ago First seen · 71 lines · 25 tokens per session scan A c7c793709b18
cost-audit is a skill published in the GitHub repository berkcangumusisik/claude-code-practices (10 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 645 once invoked, about $0.0001 per session on Opus 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.
Other skills, from other repositories
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
snip
You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.
goai
GoAI is a Go SDK for AI applications. One unified API across 25+ LLM providers. Inspired by the Vercel AI SDK, adapted to Go idioms (generics, interfaces, channels).
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.