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.
npx agentmods add instructions/pomterre/ccguard/claude-mdgit clone --depth 1 https://github.com/pomterre/ccguardWrote 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/pomterre/ccguard/claude-md)<a href="https://agentmods.dev/instructions/pomterre/ccguard/claude-md"><img src="https://agentmods.dev/badge/instructions/pomterre/ccguard/claude-md.svg" alt="Measured on agentmods" 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 | $0.00947 | $0.00947 |
| Opus 5 | $0.00474 | $0.00474 |
| Sonnet 5 | $0.00189 | $0.00189 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
ccguard 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ccguard
Project Goal
CCGuard is a Claude Code hook that enforces net-negative lines of code (LOC) changes. When Claude Code attempts to edit or write files, CCGuard:
- Captures: Intercepts Edit, MultiEdit, and Write operations
- Calculates: Counts lines added vs removed
- Validates: Checks if changes would result in net positive LOC
- Blocks: Prevents operations that increase total LOC
- Guides: Provides suggestions for reducing code
This automated enforcement encourages code simplicity and thoughtful refactoring without manual reminders.
Architecture
The project follows a clean, modular architecture:
src/
├── cli/ # CLI entry point
│ └── ccguard.ts # Main executable
├── contracts/ # TypeScript types and Zod schemas
│ ├── types.ts # Core interfaces
│ └── schemas.ts # Validation schemas
├── hooks/ # Claude Code hook processing
│ ├── processHookData.ts # Main hook processor
│ └── userPromptHandler.ts # Handle on/off commands
├── storage/ # Persistence layer
│ ├── Storage.ts # Storage interface
│ ├── FileStorage.ts # File-based implementation
│ └── MemoryStorage.ts # In-memory for testing
├── validation/ # LOC validation logic
│ ├── locCounter.ts # Line counting algorithms
│ └── validator.ts # Main validation logic
└── ccguard/ # State management
└── GuardManager.ts # Enable/disable and stats
Key Design Decisions
1. Session-Based Tracking
- Each Claude session gets its own statistics
- Cumulative tracking across all operations
- Resets don't affect other sessions
2. Line Counting Strategy
- Ignores empty lines by default (configurable)
- Counts actual code content, not whitespace
- Simple split-by-newline approach
3. Storage Abstraction
- Interface-based design for flexibility
- File storage for persistence
- Memory storage for testing
4. Validation Flow
- Pre-tool validation only (before changes applied)
- Immediate feedback on violations
- Clear, actionable error messages
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.
- 6d ago First seen · 139 lines · 947 tokens per session scan A a8fc0dee8953
ccguard CLAUDE.md is an instructions file published in the GitHub repository pomterre/ccguard (45 stars, last pushed 1y ago), licensed MIT. It adds 947 tokens to every session, about $0.0047 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.
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.
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).
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.
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.
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 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).