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 skills add juanmhidalgo/claude-plugins --skill claude-md-best-practicesgit clone --depth 1 https://github.com/juanmhidalgo/claude-pluginsWrote 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/skills/juanmhidalgo/claude-plugins/claude-md-best-practices)<a href="https://agentmods.dev/skills/juanmhidalgo/claude-plugins/claude-md-best-practices"><img src="https://agentmods.dev/badge/skills/juanmhidalgo/claude-plugins/claude-md-best-practices/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/skills/juanmhidalgo/claude-plugins/claude-md-best-practices"><img src="https://agentmods.dev/badge/skills/juanmhidalgo/claude-plugins/claude-md-best-practices.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 | $0.00042 | $0.00985 |
| Opus 5 | $0.00021 | $0.00492 |
| Sonnet 5 | $0.00008 | $0.00197 |
| Haiku 4.5 | $0.00004 | $0.00098 |
Grade A, and why
claude-md-best-practices 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 12d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md Best Practices
Consolidated guide from Anthropic's official documentation.
Core Principles
<context_window_management> The 200K context window is shared between:
- System prompt, conversation history, all CLAUDE.md files
- Commands, skills, hooks, and user's actual request
Golden rule: Only add what Claude doesn't already know. </context_window_management>
<conciseness_imperative> Target sizes:
- Small projects (< 10K LOC): 100-150 lines
- Medium projects (10-50K LOC): 150-250 lines
- Large projects (> 50K LOC): 200-300 lines
Red flags: > 400 lines, multiple 50+ line examples, repeated explanations </conciseness_imperative>
XML Tags for Structure
XML tags reduce misinterpretation by 40-60% and help Claude process structured content better.
Essential tags: <project_context>, <key_directories>, <standards>, <critical_rules>, <reference_docs>
For detailed XML patterns and examples, see patterns.md.
Memory System
<memory_hierarchy> Precedence order (higher overrides lower):
- Enterprise:
/etc/claude-code/CLAUDE.md - Project:
./CLAUDE.md - Project Rules:
./.claude/rules/*.md - User:
~/.claude/CLAUDE.md - Local:
./CLAUDE.local.md(gitignored) </memory_hierarchy>
File imports: Use @path/to/file syntax. Max depth 5 hops.
Modular rules: Use .claude/rules/*.md with optional paths: frontmatter for path-specific rules.
Essential Content
Persuasion Principles
Use these for critical rules enforcement. See persuasion.md for patterns:
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 122 lines · 42 tokens per session scan A 3d0e76ec669a
claude-md-best-practices is a skill published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 985 once invoked, about $0.0002 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 skills, from other repositories
memory-system
Design guidance for giving an AI a persistent memory system. It covers storing, finding, using, changing, and deleting information such as user preferences and project knowledge.
tool-specification
Tool specification defines how an AI discovers, describes, authorizes, and uses external tools. Tools are connected functions or services, such as APIs, browsers, or file operations.
agent-delegation
A guide for designing systems where several specialised AI agents share work. It covers dividing responsibilities, passing short task summaries, managing task stages, and checking results.
code-engineering
Design guidance for AI agents that edit code and work with files and Git. Git is a system for tracking code changes and their history.
context-management
Design guidance for managing the limited amount of text an AI can consider at once, called its context window. It covers summaries, delayed loading, persistent memory, and token budgets.
conversation-flow
Design guidance for how an AI should classify requests, choose a workflow, ask clarifying questions, and decide how independently to act.