local-token-saver: Instructions file for Claude Code

CLAUDE.md

local-token-saver CLAUDE.md is an instructions file for Claude Code from itsarmaanverma/local-token-saver. It costs 393 tokens per session, scanned A, original, MIT.

Repository instructions for a project where Claude and Codex work through sequential remediation tasks. They define how to resume work, claim tasks, inspect changes, and verify the result.

In plain words
What is it for?
Use them in the local-token-saver repository when Claude is resuming or completing a task, checking file scope, running verification, or preparing a handoff.
Why use it?
They prevent agents from overlapping work or marking incomplete changes as finished. They also preserve existing edits and require tests, linting, and benchmarks.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is itsarmaanverma/local-token-saver's own configuration. It tells Claude Code how to work on local-token-saver 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 local-token-saver configures →

Reuse

Borrowing it

Nothing to install: this file belongs to itsarmaanverma/local-token-saver. 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/itsarmaanverma/local-token-saver/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/itsarmaanverma/local-token-saver

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 local-token-saver CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/itsarmaanverma/local-token-saver/claude-md/github.svg)](https://agentmods.dev/instructions/itsarmaanverma/local-token-saver/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/itsarmaanverma/local-token-saver/claude-md"><img src="https://agentmods.dev/badge/instructions/itsarmaanverma/local-token-saver/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 local-token-saver CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/itsarmaanverma/local-token-saver/claude-md"><img src="https://agentmods.dev/badge/instructions/itsarmaanverma/local-token-saver/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 393 This file is loaded in full into every session.
When invoked 393 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 $0.00393 $0.00393
Opus 5 $0.00197 $0.00197
Sonnet 5 $0.00079 $0.00079
Haiku 4.5 $0.00039 $0.00039

Measured 9d ago against content hash aa99794e2f3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

local-token-saver 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.

CLAUDE.md · 30 lines

What it actually says

Claude Continuation Instructions

This repository is a sequential, cross-platform remediation project. Work on exactly one task at a time.

Start every session

  1. Set MESH_PLATFORM=claude.
  2. Run python C:/Users/armaa/agent-mesh/mesh.py resume --platform claude.
  3. Read docs/PHASE_PROGRESS.md and the newest .agent-mesh/handoff.md block addressed to claude or any.
  4. Run git status --short --branch and inspect any existing diff before editing.
  5. Continue only the active task, or claim the first unchecked task if none is active.

Editing and verification rules

  • Coordination mode is sequential. Do not launch parallel agents or begin a second checklist item.
  • Before editing, claim the task with agent-mesh and run mesh check for every planned file.
  • Keep implementation, tests, benchmarks, and progress updates within the active task's scope.
  • Do not mark a task complete unless targeted tests, the full suite, changed-file lint, and its benchmark pass.
  • The known baseline is 83 passed, 6 skipped, and one Windows containment failure; no earlier phase may add failures, and P02 must remove the known failure.
  • Never overwrite unrelated or pre-existing changes.

Complete or pause a task

  • Update the matching checklist entry in docs/PHASE_PROGRESS.md with a brief summary, verification evidence, and commit SHA.
  • Add two concise handoff lines describing the next task and its first command.
  • Run mesh done <task-id> and append a handoff to any; push the code and progress checkpoint.
  • Stop after the push. Do not start the next task without explicit user approval.
  • If blocked or near a usage cutoff, keep the current worktree intact, record dirty files and the next command, append a handoff, and stop.
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. 9d ago First seen · 30 lines · 393 tokens per session scan A aa99794e2f3f

Subscribe to this mod's changes

local-token-saver CLAUDE.md is an instructions file published in the GitHub repository itsarmaanverma/local-token-saver (2 stars, last pushed 1mo ago), licensed MIT. It adds 393 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.

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

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

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.

deepseek-ai/deepseek-harness · 3,735 tokens