Borrowing it
Nothing to install: this file belongs to gauravkrp/claude-contextlens. 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/gauravkrp/claude-contextlens/main/CLAUDE.mdgit clone --depth 1 https://github.com/gauravkrp/claude-contextlensWrote 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/gauravkrp/claude-contextlens/claude-md)<a href="https://agentmods.dev/instructions/gauravkrp/claude-contextlens/claude-md"><img src="https://agentmods.dev/badge/instructions/gauravkrp/claude-contextlens/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/gauravkrp/claude-contextlens/claude-md"><img src="https://agentmods.dev/badge/instructions/gauravkrp/claude-contextlens/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 | $0.00937 | $0.00937 |
| Opus 5 | $0.00468 | $0.00468 |
| Sonnet 5 | $0.00187 | $0.00187 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
claude-contextlens 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 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.
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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contextlens
Local analytics for Claude Code. Reads the JSONL transcripts already on disk and answers why usage cost what it did, not just how much it was.
Everything runs locally. No account, no API key, no upload, no telemetry. A change that sends data anywhere is wrong by definition.
Layout
packages/core ingest, normalization, SQLite, pricing, queries, config inventory
packages/server JSON API and static host (Hono)
packages/cli the published binary
apps/web Vite + React dashboard
Dependencies point one way: cli and server depend on core, apps/web
depends on nothing (it talks to the API over HTTP and redeclares its own
response types, because importing core would drag better-sqlite3 into a browser
bundle).
Commands
pnpm install && pnpm build # packages only
pnpm --filter @claude-contextlens/web build
pnpm -r typecheck
pnpm -r test
pnpm --filter @claude-contextlens/web dev # dashboard HMR, proxies /api to :4317
node packages/cli/dist/index.js serve --open # run the built CLI
Both a build and a typecheck must be clean, with zero warnings, before anything is called done.
Things that will bite you
Deduplicate or the numbers are garbage. Claude Code rewrites transcripts on
resume and compact, so the same turn appears in several files. Deduping removes
about 57% of parsed records on real data. Dedup keys are the message UUID and
the (requestId, apiMessageId) pair.
Cost is derived, never stored upstream. Transcripts carry token counts.
packages/core/src/pricing turns those into dollars at published API rates.
Never introduce a second definition of what something costs; if a query needs
cost, it sums cost_usd, and if it needs a per-provider cost it goes through
getUsageAttribution.
Costs are not the user's bill. On a Max or Pro plan they are what the same work would have billed through the API. Say so wherever a total is shown.
Never invent a status the data does not contain. Transcripts carry no
account identifier, so pre-ingest usage is unattributed rather than guessed.
Claude Code persists no MCP connection state, so nothing shows a "connected"
badge; measured calls are the honest answer. This is a product principle, not a
nicety. If you cannot know it, say you cannot know it.
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 · 97 lines · 937 tokens per session scan A 544f94fc2868
claude-contextlens CLAUDE.md is an instructions file published in the GitHub repository gauravkrp/claude-contextlens (1 stars, last pushed 1mo ago), licensed MIT. It adds 937 tokens to every session, about $0.0047 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.