context-evaluator CLAUDE.md

Project instructions for context-evaluator, including its required testing, linting, type-checking, and development commands. Linting checks code style and common errors; type-checking checks that values are used with the right data types.

In plain words
What is it for?
They are for running the project, testing changes, checking formatting and code quality, validating TypeScript types, and fixing failures.
Why use it?
They define the checks that must pass after code changes and before a commit is accepted.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/packmindhub/context-evaluator/claude-md
Clone the repo
git clone --depth 1 https://github.com/PackmindHub/context-evaluator
Per session 9,000 This file is loaded in full into every session.
When invoked 9,000 The same file — it is already loaded in full.
Security scan E 4 findings. Scan, not verified.
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 $0.09000 $0.09000
Opus 5 $0.04500 $0.04500
Sonnet 5 $0.01800 $0.01800
Haiku 4.5 $0.00900 $0.00900

Measured 3d ago against content hash a3aa5a1c5d0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade E, and why

context-evaluator CLAUDE.md scanned grade E with 4 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 3d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- rtk-instructions v2 -->

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo ufw allow 3001/tcp

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf prompts/debug/

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:3001/api/health
CLAUDE.md · 985 lines

How it starts

The opening of the file, as written. The whole thing — 985 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.


Development Workflow

After Every Code Modification

MANDATORY: Run tests after each code change to catch regressions early:

bun run test

If any tests fail, you MUST fix them before completing the task. Do not proceed to lint or consider the task done until all tests pass.

At the end of any task, also run lint and fix issues:

bun run lint

Pre-commit Hook

This project uses Husky with a pre-commit hook that runs:

  • bun run test - All tests must pass
  • bun run lint - Code must pass linting
  • bun run typecheck - TypeScript types must be valid

Commits will be blocked if any fails.


Common Commands

# Development
bun run dev              # Both API (port 3001) and frontend (port 3000)
bun run dev:api          # API server only
bun run dev:frontend     # Frontend dev server only
bun run dev:cli          # CLI mode with Claude

# Testing & Quality
bun run test             # Run all tests
bun run lint             # Biome check (lint + format)
bun run lint:fix         # Biome auto-fix
bun run format           # Biome format only
bun run typecheck        # TypeScript check

# Production Build
bun run build            # Full production build (frontend + embedded assets + all platform binaries)

# ⚠️ IMPORTANT: Do NOT use build:binaries directly
# build:binaries only compiles binaries without rebuilding frontend
# Always use the full build command above

# Evaluation
bun run evaluate         # Run CLI evaluation shorthand

# Frontend CSS/Style Changes
cd frontend && bun run css:build  # Rebuild Tailwind CSS (required after Tailwind config changes)

Frontend Style Changes

IMPORTANT: When modifying Tailwind configuration (tailwind.config.js) or adding new Tailwind utility classes, you must rebuild the CSS for changes to appear:

cd frontend
bun run css:build    # Rebuild CSS once
# OR
bun run css:watch    # Auto-rebuild on changes

Read the full file on GitHub · 985 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. 3d ago First seen · 985 lines · 9,000 tokens per session scan E a3aa5a1c5d0a

Subscribe to this mod's changes

context-evaluator CLAUDE.md is an instructions file published in the GitHub repository PackmindHub/context-evaluator (32 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 9,000 tokens to every session, about $0.0450 per session on Opus 5. A static security scan graded it E with 4 findings (hidden instructions, asks for root, recursive force delete). 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

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

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

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 · 4,345 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

next.js 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