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 nataliacorrea03/claude-code-skills --skill working-with-claudegit clone --depth 1 https://github.com/nataliacorrea03/claude-code-skillsWrote 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/nataliacorrea03/claude-code-skills/working-with-claude)<a href="https://agentmods.dev/skills/nataliacorrea03/claude-code-skills/working-with-claude"><img src="https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/working-with-claude/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/nataliacorrea03/claude-code-skills/working-with-claude"><img src="https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/working-with-claude.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 | $0.00163 | $0.04069 |
| Opus 5 | $0.00081 | $0.02034 |
| Sonnet 5 | $0.00033 | $0.00814 |
| Haiku 4.5 | $0.00016 | $0.00407 |
Grade A, and why
working-with-claude 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 11d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working with Claude
The durable, tool-independent practices for getting reliable, high-quality work out of Claude. Synthesized from nine Anthropic Academy courses (AI Fluency, AI Capabilities & Limitations, AI Fluency for Small Business, Claude 101, Claude Code 101, Claude Code in Action, Intro to Agent Skills, Intro to Subagents, Building with the Claude API). The boundaries move as models improve; the shape of this holds.
This is a reference, not a checklist to recite. Pull the section that fits the moment.
1. The 4D framework (the spine)
Every interaction with Claude runs on four competencies. They are skills you practice, not tricks that go stale.
- Delegation: decide what work stays human, what goes to Claude, and how to split it. Your own expertise is the foundation, not an afterthought.
- Description: communicate clearly. Build a thinking environment, not a clever one-liner.
- Discernment: critically evaluate what comes back: the output, the process, and how Claude behaved.
- Diligence: own the result. Verify, be transparent about AI's role, take responsibility.
It runs as two loops:
- Inner loop (Description ↔ Discernment): the day-to-day back-and-forth. Say what you need, judge what comes back, sharpen the next ask. Most real work is many small turns of this loop.
- Outer loop (Delegation ↔ Diligence): the frame around every interaction. Decide upfront what is even right to hand off, then own and verify the result.
The honest test is not "can AI do this" but "should AI do this," and "does the output meet the standard I put my name on." Research finding worth remembering: most people Describe naturally but rarely Discern. Discernment is the biggest growth area for almost everyone.
Three modes of engagement (none is better, pick by task):
- Automation: Claude completes a specific task you define.
- Augmentation: you and Claude work as thinking partners. Usually the most creative results.
- Agency: you configure Claude to act independently on your behalf.
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.
- 11d ago First seen · 188 lines · 163 tokens per session scan A 15ac4b00ff9b
working-with-claude is a skill published in the GitHub repository nataliacorrea03/claude-code-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 163 tokens to every session and 4,069 once invoked, about $0.0008 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
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
autonomous-loops
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
content-engine
Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.