Borrowing it
Nothing to install: this file belongs to FlineDev/ContextKit. 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/FlineDev/ContextKit/main/AGENTS.mdgit clone --depth 1 https://github.com/FlineDev/ContextKitWrote 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/flinedev/contextkit/agents-md)<a href="https://agentmods.dev/instructions/flinedev/contextkit/agents-md"><img src="https://agentmods.dev/badge/instructions/flinedev/contextkit/agents-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/flinedev/contextkit/agents-md"><img src="https://agentmods.dev/badge/instructions/flinedev/contextkit/agents-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 | $0.09979 | $0.09979 |
| Opus 5.5 | $0.03992 | $0.03992 |
| Sonnet 5.5 | $0.01996 | $0.01996 |
| Haiku 4.5 | $0.00998 | $0.00998 |
Grade C, and why
ContextKit AGENTS.md scanned grade C with 2 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 1mo 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
├── 📄 install.sh # GLOBAL INSTALLER (users run: curl | sh) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
├── 📄 install.sh # GLOBAL INSTALLER (users run: curl | sh) How it starts
The opening of the file, as written. The whole thing — 1,051 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ContextKit Repository Development Guide
🚨 CRITICAL: Meta-Development Context
You are working ON ContextKit, not WITH ContextKit!
This repository contains TEMPLATES and INSTALLATION SCRIPTS that other developers will use. The files here are NOT meant to be executed directly in this repository - they are source templates that get copied to user systems during installation.
🧠 Understanding the Meta-Architecture
ContextKit is a "template distribution system" - this repository contains:
- Templates - Files that get copied and customized during installation
- Installation scripts - Logic that copies templates to user systems
- Documentation - Explains how the system works
Key Mental Model: Think of this repository as a "template factory" that produces customized development environments for other projects.
📂 Complete Repository Structure & Purpose
ContextKit/
├── 📄 install.sh # GLOBAL INSTALLER (users run: curl | sh)
├── 📖 README.md # Public documentation
├── 📖 CLAUDE.md # This file - development guidance for AI assistants
├── 📖 LICENSE # MIT license
├── 📄 CHANGELOG.md # Version tracking and migration support
└── 🎯 Templates/ # TEMPLATE DISTRIBUTION CENTER
├── Guidelines/ # → GLOBAL CODING STANDARDS (copied by install.sh)
│ ├── Swift.md # Swift patterns
│ └── SwiftUI.md # SwiftUI patterns
├── Commands/ # → CLAUDE CODE COMMANDS (get copied during /ctxk:proj:init)
│ ├── proj/ # Project management commands
│ │ ├── init.md # Project initialization
│ │ ├── init-workspace.md # Workspace configuration
│ │ └── migrate.md # Version updates
│ ├── plan/ # Feature planning workflow
│ │ ├── 1-spec.md # Business requirements
│ │ ├── 2-research-tech.md # Technical research and architecture
│ │ └── 3-steps.md # Implementation breakdown
│ ├── impl/ # Development workflow
│ │ ├── start-working.md # Context-aware development start
│ │ ├── commit-changes.md # Smart commit message generation
│ │ ├── release-app.md # iOS/macOS App Store releases
│ │ └── release-package.md # Swift Package releases
│ └── bckl/ # Backlog management
│ ├── add-idea.md # Capture new ideas with evaluation
│ ├── add-bug.md # Bug report with impact assessment
│ ├── prioritize-ideas.md # Organize ideas backlog
│ ├── prioritize-bugs.md # Triage bugs backlog
│ ├── remove-idea.md # Remove completed ideas from backlog
│ └── remove-bug.md # Remove fixed bugs from backlog
├── Scripts/ # → ALL SCRIPTS (hooks & standalone, get copied during /ctxk:proj:init)
│ ├── AutoFormat.sh # Auto-format edited Swift files (PostToolUse hook)
│ ├── VersionStatus.sh # Version checking and status display (SessionStart hook)
│ └── CustomStatusline.sh # Complete statusline script with 5h-usage tracking and colored progress bars
├── Agents/ # → AI ASSISTANTS (get copied during /ctxk:proj:init)
│ ├── build-project.md # [READY] Execute builds with constitutional compliance checking
│ ├── check-accessibility.md # [INCOMPLETE] Accessibility compliance validation (VoiceOver, contrast, etc.)
│ ├── check-localization.md # [INCOMPLETE] Localization readiness audit (String Catalog, cultural adaptation)
│ ├── check-error-handling.md # [INCOMPLETE] ErrorKit pattern validation and typed throws
│ ├── check-modern-code.md # [INCOMPLETE] API modernization (Date.now, Duration, async/await)
│ ├── check-code-debt.md # [INCOMPLETE] Technical debt cleanup and code consolidation
│ ├── run-test-suite.md # [READY] Execute complete test suite with build validation and structured failure reporting
│ └── run-specific-test.md # [READY] Execute specific test with build validation and focused failure analysis
├── Features/ # → FEATURE TEMPLATES (used by /ctxk:plan:1-spec, /ctxk:plan:quick, etc.)
│ ├── Spec.md # Business requirements and user stories (spec-kit methodology)
│ ├── Tech.md # Technical architecture and constitutional compliance
│ ├── Steps.md # Implementation task breakdown with parallel markers [P]
│ └── Quick.md # Quick task planning template with interactive validation
├── Contexts/ # → CONTEXT TEMPLATES (used by /ctxk:proj:init and /ctxk:proj:init-workspace)
│ ├── Project.md # Project-level Context.md with ContextKit configuration
│ └── Workspace.md # Workspace-level Context.md with client/company overrides
├── Backlog/ # → BACKLOG TEMPLATES (used by /ctxk:bckl:add-idea and /ctxk:bckl:add-bug)
│ ├── Ideas-Inbox.md # New idea capture template with evaluation framework
│ ├── Ideas-Backlog.md # Prioritized idea backlog template with strategic organization
│ ├── Bugs-Inbox.md # Bug report intake template with impact assessment
│ └── Bugs-Backlog.md # Triaged bug backlog template with severity-based organization
├── Formatters/ # → CODE STYLE CONFIGS (get copied during /ctxk:proj:init)
│ ├── .swift-format # Apple swift-format configuration
│ └── .swiftformat # SwiftFormat (Nick Lockwood) configuration
└── settings.json # → CLAUDE CODE SETTINGS TEMPLATE
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.
- 1mo ago First seen · 1,051 lines · 9,979 tokens per session scan C 761fd8d2e373
ContextKit AGENTS.md is an instructions file published in the GitHub repository FlineDev/ContextKit (167 stars, last pushed 7mo ago), licensed MIT. It adds 9,979 tokens to every session, about $0.0399 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.