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 agentmods add instructions/studiozedward/pip-token/claude-mdgit clone --depth 1 https://github.com/studiozedward/pip-tokenWrote 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/studiozedward/pip-token/claude-md)<a href="https://agentmods.dev/instructions/studiozedward/pip-token/claude-md"><img src="https://agentmods.dev/badge/instructions/studiozedward/pip-token/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 | $0.00689 | $0.00689 |
| Opus 5 | $0.00345 | $0.00345 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
pip-token CLAUDE.md 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 4d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pip-Token — Project Conventions
A VS Code extension that helps Claude Code users track their token usage with a Fallout Pip-Boy aesthetic.
Tech stack
TypeScript, VS Code Extension API, SQLite (better-sqlite3), plain HTML/CSS in the webview. No frontend frameworks. No chart libraries. No network calls.
Commands
npm install— install dependenciesnpm run build— compile and bundle with esbuildnpm run watch— dev modenpm test— run Vitest testsnpm run package— build .vsix- F5 in VS Code — launch the extension in a development host
Branching and commits
mainis always shippable- Feature branches off main, named
feat/short-descriptionorfix/short-description - Squash-merge into main via PR
- Conventional Commits:
feat: ...,fix: ...,docs: ...,refactor: ...,test: ...,chore: ...
Where things live
- Product spec:
docs/DESIGN.md(authoritative) - Screenshots:
mockups/screenshots/*.png(current state of the extension) - Terminology:
docs/GLOSSARY.md - Architecture:
docs/ARCHITECTURE.md - Decisions made and why:
docs/decisions/ - Lessons learned during build:
LESSONS.md— read this before tackling areas marked as "previously problematic"
Subdirectory CLAUDE.md files
Pip-Token uses a distributed CLAUDE.md pattern. When working in src/parsing/, src/webview/, src/data/, src/domain/, or test/, also read the local CLAUDE.md in that directory — it contains conventions specific to that subsystem.
Session identity
A "session" in Pip-Token maps 1:1 to a Claude Code sessionId. Clearing context in Claude Code starts a new session with a new ID — this is intentional, not a bug. Context window utilisation and cache state are per-session and cannot be meaningfully merged across sessions. The "All Projects" aggregate on LIVE/SESSION sums token counts from the turns table across all active sessions (not from window counters, which break across rate-limit boundaries and resyncs).
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.
- 4d ago First seen · 53 lines · 689 tokens per session scan A 14681c11a08c
pip-token CLAUDE.md is an instructions file published in the GitHub repository studiozedward/pip-token (10 stars, last pushed 4mo ago), licensed MIT. It adds 689 tokens to every session, about $0.0034 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 instructions, from other repositories
awesome-vscode CLAUDE.md
Instructions for viatsko/awesome-vscode, covering claude.md, what this repo is, adding an entry, themes and linting / ci.
vscode-peacock AGENTS.md
AGENTS.md instructions for johnpapa/vscode-peacock, covering peacock — agent guide, project overview, repository structure, tech stack and build & run.
vscode-peacock copilot-instructions.md
Copilot instructions for johnpapa/vscode-peacock, covering copilot instructions — peacock, project type, typescript conventions, vs code extension patterns and color handling.
vscode-gitlens AGENTS.md
AGENTS.md instructions for gitkraken/vscode-gitlens, covering gitlens development guide, working style expectations, development environment, development commands and git & repository guidelines.
calva-backseat-driver AGENTS.md
Instructions for BetterThanTomorrow/calva-backseat-driver, covering calva backseat driver - ai agent guide, essential architecture, action/effect system ("ex"), runtime state structure and datascript connections.
walkerOS CLAUDE.md
Claude Code instructions for elbwalker/walkerOS, covering claude.md and important: use agent.md.