Borrowing it
Nothing to install: this file belongs to PavelTkachenk0/ContextTax. 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/PavelTkachenk0/ContextTax/main/CLAUDE.mdgit clone --depth 1 https://github.com/PavelTkachenk0/ContextTaxWrote 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/paveltkachenk0/contexttax/claude-md)<a href="https://agentmods.dev/instructions/paveltkachenk0/contexttax/claude-md"><img src="https://agentmods.dev/badge/instructions/paveltkachenk0/contexttax/claude-md/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/instructions/paveltkachenk0/contexttax/claude-md"><img src="https://agentmods.dev/badge/instructions/paveltkachenk0/contexttax/claude-md.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 | $0.00400 | $0.00400 |
| Opus 5 | $0.00200 | $0.00200 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
ContextTax 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 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.
What it actually says
ContextTax
Measures the context-window tax an MCP server / tool imposes on an agent —
schema bloat and response bloat, across the full token lifecycle — with
ground-truth accuracy. Full concept: .claude/memory-bank/product-brief.md.
Hard rules (do not break)
- Public repo. Never commit secrets, API keys, or personal absolute paths.
The Anthropic key is read from
ANTHROPIC_API_KEY(env) ordotnet user-secrets— never from a committed file. - Ground-truth tokens. Count with Anthropic
count_tokens+ realusage(incl. cache tokens). Never estimate Claude tokens withtiktoken. - Internal process docs are local-only.
docs/superpowers/is gitignored.
Commands
- Build:
dotnet build - Test:
dotnet test - Format check:
dotnet format --verify-no-changes - Run CLI:
dotnet run --project src/ContextTax.Cli - Run web:
dotnet run --project src/ContextTax.Web
Map (load on demand)
- Concept / why →
.claude/memory-bank/product-brief.md - Architecture / where things live →
.claude/memory-bank/architecture.md - Conventions (code/test/commit/hygiene) →
.claude/memory-bank/conventions.md - Why we chose X →
.claude/memory-bank/decisions/ - Status / what's next →
.claude/memory-bank/roadmap.md - Specs & plans (local) →
docs/superpowers/
Workflow loop
brainstorm → spec → plan → implement → /sync-memory (fold the plan's outcomes
back into the memory bank). TDD per superpowers:test-driven-development.
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 · 33 lines · 400 tokens per session scan A 301fbbf1c60b
ContextTax CLAUDE.md is an instructions file published in the GitHub repository PavelTkachenk0/ContextTax (5 stars, last pushed 3mo ago), licensed MIT. It adds 400 tokens to every session, about $0.0020 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
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.