CacheLane: Instructions file for Claude Code

CLAUDE.md

CacheLane CLAUDE.md is an instructions file for Claude Code from Aditya-Tripuraneni/CacheLane. It costs 1,537 tokens per session, scanned A, original, Apache-2.0.

Project instructions for CacheLane, a local server and set of Claude Code hooks that reduce repeated prompt data sent to Anthropic’s API. Prompt caching stores reusable parts of a request, while pruning replaces old tool results with references that can be fetched again.

In plain words
What is it for?
Use them when implementing or reviewing CacheLane’s request organization, prompt-cache breakpoints, tool-result pruning, data flow, API contracts, or related designs.
Why use it?
They show where the implementation specifications live and what to read before changing a system that affects token usage and long coding sessions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions subagents; mentions Claude Code.

This is Aditya-Tripuraneni/CacheLane's own configuration. It tells Claude Code how to work on CacheLane itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything CacheLane configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Aditya-Tripuraneni/CacheLane. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Aditya-Tripuraneni/CacheLane/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Aditya-Tripuraneni/CacheLane

Made for: Claude Code.

Wrote 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.

agentmods badge for CacheLane CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aditya-tripuraneni/cachelane/claude-md/github.svg)](https://agentmods.dev/instructions/aditya-tripuraneni/cachelane/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/aditya-tripuraneni/cachelane/claude-md"><img src="https://agentmods.dev/badge/instructions/aditya-tripuraneni/cachelane/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.

agentmods 80×15 button for CacheLane CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/aditya-tripuraneni/cachelane/claude-md"><img src="https://agentmods.dev/badge/instructions/aditya-tripuraneni/cachelane/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,537 This file is loaded in full into every session.
When invoked 1,537 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01537 $0.01537
Opus 5 $0.00768 $0.00768
Sonnet 5 $0.00307 $0.00307
Haiku 4.5 $0.00154 $0.00154

Measured 10d ago against content hash 74b02b7958fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

CacheLane 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 10d 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.

CLAUDE.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cachelane — Project Context for Claude/Agent Sessions

Cachelane is a local MCP server + Claude Code hooks (PreRequest/PostResponse) that intercepts traffic between Claude Code and api.anthropic.com to reduce input-token costs on every turn.

Two mechanisms:

  1. Cache-aware orchestration — reorders prompt blocks into three volatility regions and places two cache_control breakpoints so the Anthropic prompt cache fires at 0.1x instead of 1.0x.
  2. K-pruning — replaces tool-call result blocks idle for ≥ K consecutive turns with refetchable stubs (non-lossy), flattening token growth in long sessions.

Where to Start

All implementation-ready specs live in /designs/. Read them in order before touching code:

File What it answers
designs/README.md Full index + reading order
designs/01-system-overview.md Goals, non-goals, glossary
designs/02-architecture.md Components, data flows, all 7 diagrams
designs/03-engineering-specs.md All requirements (REQ-F / REQ-NF), API contracts, data models
designs/04-turns-and-pruning.md K-pruning algorithm, pseudocode, worked examples
designs/05-token-reduction.md Research rationale, ADRs, performance targets
designs/06-systems-design.md Tech stack, modules, schemas, milestones, runbook
designs/07-open-questions.md Remaining open questions with owners
designs/decisions/ Individual ADR files

Critical Invariants (do not violate without updating the spec)

  • Pipeline order: Classifier → Pruner → Reorderer (this order is canonical; Pruner must run before Reorderer because pruning changes block token counts and volatility before breakpoints are computed).
  • Vocabulary: STABLE | SEMI | VOLATILE — these are the only accepted names for volatility classes everywhere (spec, code, logs, tests, comments).
  • Naming: storage and API-contract types use snake_case (e.g. the Block interface, PrefixState, blocks/turns/block_references rows, CachelaneConfig fields, SQLite columns). In-process working types (function parameters, local helpers) may use camelCase. Rule of thumb: if it crosses a process / storage / network boundary, snake_case.
  • Source of truth on drift: when in-repo synthesized specs in /designs/ conflict with the binding source docs (Cachelane_Systems_Design_Document.docx, Cachelane_Phase2_Engineering_Specifications_v2.docx; pre-extracted text under /tmp/cachelane-extracts/), the binding .docx wins. Fix the synthesis upstream first, then the code — otherwise drift recurs on the next milestone.
  • Fail-open: any error in Cachelane must return the unmutated request to Claude Code. Never silently drop a turn or block the model.
  • Local-only: no prompt content, API keys, or user data leave api.anthropic.com's direct request path. No hosted backend.
  • Cache-stability gate: SHA-256 of the prefix region must be byte-identical across 3 consecutive identical-input runs. This gate blocks merge on failure — no exceptions.

Read the full file on GitHub · 78 lines

Changes

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.

  1. 10d ago First seen · 78 lines · 1,537 tokens per session scan A 74b02b7958fc

Subscribe to this mod's changes

CacheLane CLAUDE.md is an instructions file published in the GitHub repository Aditya-Tripuraneni/CacheLane (20 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,537 tokens to every session, about $0.0077 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 2026-08-30.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens