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/module-federation/core/claude-mdgit clone --depth 1 https://github.com/module-federation/coreWhat 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 | $0.03933 | $0.03933 |
| Opus 5 | $0.01966 | $0.01966 |
| Sonnet 5 | $0.00787 | $0.00787 |
| Haiku 4.5 | $0.00393 | $0.00393 |
Grade A, and why
core 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 yesterday.
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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Task Parallelization & Development Guidelines
Core Principles
Maximum Parallelization Strategy
- ALWAYS PARALLELIZE: Break down ANY task into multiple parallel sub-tasks
- IMMEDIATE EXECUTION: Launch parallel Task agents immediately without asking questions
- NO CLARIFICATION: Skip asking about implementation details unless absolutely critical
- CONTEXT EFFICIENCY: Each task handles only its specific scope to minimize token usage
Universal Parallel Task Patterns
For Any Codebase Task
Analyze the request and immediately split into parallel tasks based on:
-
File Type Separation
- Source code files
- Test files
- Configuration files
- Documentation files
- Build/deployment files
-
Functional Separation
- Core implementation
- Helper/utility functions
- Integration points
- Data models/schemas
- External interfaces
-
Directory-Based Separation
- Different modules/packages
- Frontend vs backend
- Library vs application code
- Public vs private APIs
Dynamic Task Allocation Examples
Example 1: Feature Implementation (5-7 parallel tasks)
- Task 1: Core feature logic
- Task 2: Supporting utilities/helpers
- Task 3: Tests (if applicable)
- Task 4: Integration with existing code
- Task 5: Configuration updates
- Task 6: Type definitions (if typed language)
- Task 7: Remaining changes and coordination
Example 2: Bug Investigation (3-10 parallel tasks)
- Task 1: Search for error patterns in logs/code
- Task 2: Analyze related test files
- Task 3: Check recent commits/changes
- Task 4: Investigate similar issues in codebase
- Task 5: Review documentation/comments
Example 3: Refactoring (4-6 parallel tasks)
- Task 1: Identify all usage locations
- Task 2: Plan new structure
- Task 3: Update core implementations
- Task 4: Update dependent code
- Task 5: Update tests
- Task 6: Verify no breaking changes
Example 4: Codebase Analysis (5-8 parallel tasks)
- Task 1: Analyze file structure
- Task 2: Review core business logic
- Task 3: Map dependencies
- Task 4: Identify patterns/conventions
- Task 5: Review configuration
- Task 6: Analyze build system
- Task 7: Check documentation
- Task 8: Security/performance patterns
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.
- yesterday First seen · 341 lines · 3,933 tokens per session scan A 47644565a84e
core CLAUDE.md is an instructions file published in the GitHub repository module-federation/core (2,625 stars, last pushed yesterday), licensed MIT. It adds 3,933 tokens to every session, about $0.0197 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.
Other instructions, from other repositories
magicui AGENTS.md
Instructions for magicuidesign/magicui, covering project context, key principles, before writing code, rules and accessibility (a11y).
safe-wallet-monorepo AGENTS.md
AGENTS.md instructions for safe-global/safe-wallet-monorepo, covering ai contributor guidelines, nested guidance, quick start, install dependencies (uses yarn 4 via corepack) and run web app in development mode.
storefront AGENTS.md
AGENTS.md instructions for saleor/storefront, covering saleor paper — agent guide (always-on), how to get context (read in this order; stop when answered), precedence, critical commands and non-negotiable rules.
CodeReel CLAUDE.md
Instructions for eddiejaoude/CodeReel, covering codereel, core architectural rule (important), diff view (steps mode), key files and 3d effects roadmap.
serverless-full-stack-webapp-starter-kit AGENTS.md
AGENTS.md instructions for aws-samples/serverless-full-stack-webapp-starter-kit, covering agents.md, commands, install all dependencies, webapp and cdk.
safe-wallet-monorepo CLAUDE.md
Claude Code instructions for safe-global/safe-wallet-monorepo: Read @AGENTS.md for comprehensive guidelines on contributing to this repository.