Borrowing it
Nothing to install: this file belongs to DvirNaaman/dvir-token-manager. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DvirNaaman/dvir-token-manager/main/CLAUDE.mdgit clone --depth 1 https://github.com/DvirNaaman/dvir-token-managerWrote 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/instructions/dvirnaaman/dvir-token-manager/claude-md)<a href="https://agentmods.dev/instructions/dvirnaaman/dvir-token-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/dvirnaaman/dvir-token-manager/claude-md.svg" alt="Measured on agentmods" 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 | $0.00938 | $0.00938 |
| Opus 5 | $0.00469 | $0.00469 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
dvir-token-manager CLAUDE.md scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://127.0.0.1:8080/api/overview # sanity-check an endpoint How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working in this repository.
Project overview
Dvir Token Manager ("מנהל הטוקנים | DN") - a Hebrew/RTL local dashboard for tracking Claude Code token usage, costs, and session history. Reads the JSONL transcripts Claude Code writes to ~/.claude/projects/ and turns them into per-prompt cost analytics, tool/file heatmaps, subagent attribution, cache analytics, project comparisons, and a rule-based tips engine.
Adapted from a permissively-licensed upstream codebase. The UI, language, and brand are fully owned by Dvir Naaman; the underlying engine is MIT (see LICENSE).
Status
Working codebase. 82 Python unit tests (python -m unittest discover tests). Seven UI tabs wired up: סקירה כללית, פרומפטים, שיחות, פרויקטים, מיומנויות, טיפים לחיסכון, הגדרות. Runs on Windows, macOS, and Linux.
Last full review and refresh pass: 2026-08-13. See the "Refresh, 2026-08-13" section of README.md for what changed and why.
Invariants worth knowing before editing
pricing.jsonis the only place rates live. Do not hardcode a per-token price anywhere else;tips.pyused to, and the numbers went stale without anything failing. Model ids go throughpricing.normalize_modelfirst, which strips a[1m]-style context suffix and a-YYYYMMDDsnapshot suffix so both price as the base model.- The SSE stream fans out.
server.publish()writes to one bounded queue per connected client. Do not go back to a single shared queue:queue.get()pops, so one shared queue starves every tab but one, silently. turnscounts user messages, not sessions. The Hebrew label is "פניות"; "שיחות" is reserved forsessions.- The CLI writes UTF-8 deliberately. Anything reading its output through a pipe must decode UTF-8 explicitly, or a Hebrew Windows locale decodes with cp1255 and the output is lost.
Architecture
cli.py→token_dashboard/scanner.py→~/.claude/token-dashboard.db(SQLite)token_dashboard/server.pyexposes JSON APIs (/api/*) + SSE stream (/api/stream) + static frontend (web/)web/is vanilla JS, no build step - hash router + ECharts (vendored atweb/echarts.min.js)web/assets/brand/- DN logo and faviconweb/assets/fonts/- self-hosted Heebo (hebrew + latin + latin-ext)
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.
- 8d ago First seen · 54 lines · 938 tokens per session scan A 0218fcc750d7
dvir-token-manager CLAUDE.md is an instructions file published in the GitHub repository DvirNaaman/dvir-token-manager (4 stars, last pushed 26d ago), licensed MIT. It adds 938 tokens to every session, about $0.0047 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.