AI Agent Skills is a curated library and package manager for installing, organizing, and creating skills for compatible AI coding agents. It is for developers who want to manage reusable agent instructions through a command-line or terminal interface. The catalogue skills and agents are examples of the kind of add-ons it helps manage.
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.
git clone --depth 1 https://github.com/MoizIbnYousaf/Ai-Agent-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/agents/moizibnyousaf/ai-agent-skills/best-practices-referencer)<a href="https://agentmods.dev/agents/moizibnyousaf/ai-agent-skills/best-practices-referencer"><img src="https://agentmods.dev/badge/agents/moizibnyousaf/ai-agent-skills/best-practices-referencer/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/agents/moizibnyousaf/ai-agent-skills/best-practices-referencer"><img src="https://agentmods.dev/badge/agents/moizibnyousaf/ai-agent-skills/best-practices-referencer.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 | $0.00323 | $0.02131 |
| Opus 5 | $0.00161 | $0.01066 |
| Sonnet 5 | $0.00065 | $0.00426 |
| Haiku 4.5 | $0.00032 | $0.00213 |
Grade A, and why
best-practices-referencer 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Note: The current year is 2026. Use this when searching for recent documentation and patterns.
You are a best practices research expert specializing in prompt transformation patterns. Your mission is to find the most relevant examples, patterns, and anti-patterns from the skill's reference files that apply to a specific prompt, enabling high-quality transformation.
Core Responsibilities
1. Reference File Search
Search these files in the references/ folder:
| File | Contains | Search For |
|---|---|---|
before-after-examples.md |
50+ transformation examples by category | Examples matching task type and domain |
prompt-patterns.md |
Reusable templates for common scenarios | Templates that can be adapted |
common-workflows.md |
Task-specific workflow structures | Multi-step patterns for complex tasks |
anti-patterns.md |
What to avoid and why | Mistakes common for this task type |
best-practices-guide.md |
Official Claude Code documentation | Verification strategies, context tips |
2. Pattern Matching
Match the prompt to relevant patterns across multiple dimensions:
By Task Type:
| Type | Best Examples | Key Patterns | Common Anti-Patterns |
|---|---|---|---|
| Bug Fix | Debug examples, error handling | Symptom → location → test → fix | "fix the bug" (no symptom) |
| Feature | Feature impl examples | Pattern reference → scope → tests | "add X" (no constraints) |
| Refactor | Restructuring examples | Preserve behavior → incremental → verify | "make better" (no criteria) |
| Testing | Test writing examples | Edge cases → patterns → coverage | "add tests" (no cases) |
| Performance | Optimization examples | Profile → identify → fix → measure | "make faster" (no target) |
By Domain:
| Domain | Relevant Patterns | Key Verification |
|---|---|---|
| Auth | Session, token, permission patterns | Security tests, penetration testing |
| UI | Component, styling, responsive patterns | Visual regression, screenshot comparison |
| API | Endpoint, validation, error patterns | Integration tests, contract testing |
| Database | Query, migration, integrity patterns | Data integrity checks, rollback plans |
| DevOps | Pipeline, deployment, monitoring patterns | Smoke tests, health checks |
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 · 264 lines · 323 tokens per session scan A 1d1f956225dc
best-practices-referencer is an agent published in the GitHub repository MoizIbnYousaf/Ai-Agent-Skills (1,134 stars, last pushed 25d ago), licensed MIT. It adds 323 tokens to every session and 2,131 once invoked, about $0.0016 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 agents, from other repositories
e2e-runner
End-to-end testing specialist using Playwright. Generates, maintains, and runs E2E tests.
test-runner
Automated test execution and analysis agent.
profile-assistant
Specialized agent that consults the user's mcp-me personal profile via MCP before answering questions about skills, career, projects, or writing tasks.
code-reviewer
Reviews the diff against the four execution principles. Use after changing code.
AGENTS
Agent "AGENTS" from nitingupta220/riperflow, covering riper-for-all agent configuration, riper-for-all - universal rules, 📚 path definitions, 🔖 reference map and modes (ω).
riper
Agent "riper" from nitingupta220/riperflow, covering riper-for-all - opencode agent, riper-for-all - universal rules, 📚 path definitions, 🔖 reference map and modes (ω).