ecotokens: Instructions file for Claude Code

.github/copilot-instructions.md

ecotokens copilot-instructions.md is an instructions file for Claude Code, GitHub Copilot from hansipie/ecotokens. It costs 1,195 tokens per session, scanned B, original, MIT.

Project guidance for ecotokens, a tool that reduces the amount of command output sent to Claude Code and Gemini CLI. It also tracks the tokens saved.

In plain words
What is it for?
Building and testing the Rust project, running formatting and lint checks, and installing or removing its Claude Code and Gemini CLI hooks.
Why use it?
Long shell output can use up an AI assistant’s context and token budget. These instructions explain how to build, test, check, and install ecotokens.

Instructions file for Claude CodeGitHub Copilot

Written for Claude Code and GitHub Copilot: PreToolUse hook event, but also a Copilot instructions file. Also seen: reads .claude/ paths; mentions Claude Code; mentions Gemini CLI.

This is hansipie/ecotokens's own configuration. It tells Claude Code and GitHub Copilot how to work on ecotokens 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 ecotokens configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hansipie/ecotokens. 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/hansipie/ecotokens/master/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/hansipie/ecotokens

Made for: Claude Code, GitHub Copilot.

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 ecotokens copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hansipie/ecotokens/copilot-instructions.svg)](https://agentmods.dev/instructions/hansipie/ecotokens/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/hansipie/ecotokens/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/hansipie/ecotokens/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,195 This file is loaded in full into every session.
When invoked 1,195 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.01195 $0.01195
Opus 5 $0.00598 $0.00598
Sonnet 5 $0.00239 $0.00239
Haiku 4.5 $0.00120 $0.00120

Measured 7d ago against content hash da1457c7ea5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

ecotokens copilot-instructions.md scanned grade B with 1 finding 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 7d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

ecotokens install --target gemini # Gemini CLI (writes BeforeTool hook + mcpServers in ~/.gemini/settings.json)
.github/copilot-instructions.md · 97 lines

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.

ecotokens — Copilot Instructions

What this project does

ecotokens is a token-saving companion for Claude Code and Gemini CLI. It intercepts bash/shell command outputs before they reach the model, compresses them with family-specific filters, and records how many tokens were saved.

Commands

# Build
cargo build

# Test full suite
cargo test

# Test a single integration or unit test file (no .rs suffix)
cargo test --test filter_git_test
cargo test --test gain_tui_test

# Lint (warnings are errors)
cargo clippy -- -D warnings

# Format check (required before push)
cargo fmt --check
cargo fmt

# Pre-push one-liner
cargo fmt --check && cargo clippy -- -D warnings && cargo test

# Install ecotokens hook
ecotokens install --target claude    # Claude Code only
ecotokens install --target gemini    # Gemini CLI (writes BeforeTool hook + mcpServers in ~/.gemini/settings.json)
ecotokens install --target all       # all targets
ecotokens uninstall --target gemini  # remove Gemini registration

Architecture

The project is organized into 12 modules, each with a mod.rs exporting its public API:

Module Role
filter/ Family-specific output compression (Git, Cargo, Python, C++, FS, Markdown, ConfigFile, Generic)
hook/ Handles hook stdin→stdout for Claude Code (PreToolUse, ecotokens hook), Gemini CLI (BeforeTool, ecotokens hook-gemini), and Qwen Code (PreToolUse, ecotokens hook-qwen)
metrics/ Appends Interception records to ~/.config/ecotokens/metrics.jsonl; aggregates for reports
tokens/ count_tokens(s) — dispatches to tiktoken-rs cl100k_base (exact-tokens feature) or estimate_tokens heuristic (chars * 0.25) by default
search/ Tantivy BM25 index + tree-sitter symbol extraction; chunk size 50 lines
trace/ Call graph queries (callers/callees) over the search index
tui/ Ratatui dashboards (gain, outline, trace, progress, watch)
mcp/ JSON-RPC stdio server (rmcp crate) exposing 4 tools
config/ TOML settings at ~/.config/ecotokens/settings.toml; all fields optional with defaults
masking/ Regex-based PII/secret redaction (AWS keys, GitHub PATs, JWTs, .env secrets, etc.)
install/ Idempotent hook + MCP registration for Claude Code (~/.claude/settings.json + ~/.claude.json) and Gemini CLI (~/.gemini/settings.json)
daemon/ notify-based file watcher; debounces 500 ms before reindexing

Read the full file on GitHub · 97 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. 7d ago First seen · 97 lines · 1,195 tokens per session scan B da1457c7ea5b

Subscribe to this mod's changes

ecotokens copilot-instructions.md is an instructions file published in the GitHub repository hansipie/ecotokens (20 stars, last pushed 1mo ago), licensed MIT. It adds 1,195 tokens to every session, about $0.0060 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

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 · 5,182 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

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

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

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

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