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 Tyler-R-Kendrick/agent-skills --skill aigit clone --depth 1 https://github.com/Tyler-R-Kendrick/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/skills/tyler-r-kendrick/agent-skills/ai)<a href="https://agentmods.dev/skills/tyler-r-kendrick/agent-skills/ai"><img src="https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/ai/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/tyler-r-kendrick/agent-skills/ai"><img src="https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/ai.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 | $0.00150 | $0.01083 |
| Opus 5.5 | $0.00060 | $0.00433 |
| Sonnet 5.5 | $0.00030 | $0.00217 |
| Haiku 4.5 | $0.00015 | $0.00108 |
Grade A, and why
ai 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 2mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Protocols & Standards
Overview
This skill covers the emerging ecosystem of open standards and protocols for AI agents. These specifications define how agents discover capabilities, communicate with each other, make payments, render UI, and are described declaratively.
Protocol Landscape
| Protocol | Purpose | Maintained By |
|---|---|---|
| MCP | Tool integration — how agents use tools and access context | Anthropic |
| A2A | Agent-to-agent communication and task delegation | |
| ACP | REST-based agent communication (merged into A2A) | IBM / BeeAI / Linux Foundation |
| Agent Skills | Skill packaging — how capabilities are discovered and loaded | Anthropic |
| Improve | Agent and LLM eval contracts, synthetic simulation data, and self-improvement pipelines for prompts, code, skills, agents, harnesses, and workflows | AgentEvals / AgentV / Simula / QDC / GEPA / Trace / VISTA / SkillOpt / Agent Lightning / ResponsibleAI |
| AGENTS.md | Project-level guidance for coding agents | Community |
| ADL | Declarative agent definition (identity, tools, permissions) | Next Moca / Eclipse LMOS |
| x402 | HTTP-native micropayments using stablecoins | Coinbase |
| AP2 | Secure agent-driven commerce and purchases | |
| MCP Apps | Rich interactive UI served by MCP servers | Anthropic |
| cagent | Multi-agent runtime with YAML configuration | Docker |
| learn | Feedback-to-steering workflow for generalized agent reasoning preferences | Local |
How They Relate
┌─────────────────────────────────────────────┐
│ Agent Definition (ADL, AGENTS.md) │
│ "What the agent is and what it can do" │
├─────────────────────────────────────────────┤
│ Capability Discovery (Agent Skills, MCP) │
│ "How agents find and load tools/skills" │
├─────────────────────────────────────────────┤
│ Agent Communication (A2A, ACP) │
│ "How agents talk to each other" │
├─────────────────────────────────────────────┤
│ Payments (x402, AP2) │
│ "How agents pay for services" │
├─────────────────────────────────────────────┤
│ UI (MCP Apps) │
│ "How agents render interactive interfaces" │
├─────────────────────────────────────────────┤
│ Runtime (cagent) │
│ "How agents are orchestrated and executed" │
└─────────────────────────────────────────────┘
What ships with it
60 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.
- a2a/AGENTS.md 3.4 KB
- a2a/metadata.json 611 B
- a2a/README.md 602 B
- a2a/rules/_sections.md 1.1 KB
- a2a/rules/_template.md 362 B
- a2a/rules/a2a-combine-a2a-with-mcp.md 332 B
- a2a/rules/a2a-handle-the-input-required-status-to-support-interactive.md 404 B
- a2a/rules/a2a-implement-idempotency-on-task-ids-so-retries-don-t-create.md 375 B
- a2a/rules/a2a-publish-an-agent-card-with-accurate-skill-descriptions-so.md 412 B
- a2a/rules/a2a-use-streaming-tasks-sendsubscribe-for-long-running.md 385 B
- a2a/SKILL.md 4.1 KB
- acp/AGENTS.md 6.0 KB
- acp/metadata.json 666 B
- acp/README.md 628 B
- acp/rules/_sections.md 1.3 KB
- acp/rules/_template.md 362 B
- acp/rules/acp-attach-trajectorymetadata-to-parts-when-exposing.md 362 B
- acp/rules/acp-since-acp-has-merged-into-a2a-evaluate-a2a-for-greenfield.md 421 B
- acp/rules/acp-use-get-agents-for-runtime-discovery-so-clients-can.md 406 B
- acp/rules/acp-use-redis-or-postgresql-backends-in-production-for-high.md 394 B
- acp/rules/acp-use-sessions-for-multi-turn-workflows.md 336 B
- acp/rules/acp-use-streaming-mode-for-long-running-agents-to-give-callers.md 373 B
- acp/SKILL.md 6.8 KB
- adl/AGENTS.md 3.9 KB
- adl/metadata.json 690 B
- adl/README.md 648 B
- adl/rules/_sections.md 1.3 KB
- adl/rules/_template.md 362 B
- adl/rules/adl-declare-dependencies-on-other-agents-explicitly-so-the.md 383 B
- adl/rules/adl-define-permissions-explicitly.md 321 B
- adl/rules/adl-include-governance-metadata-owner-review-status-for.md 371 B
- adl/rules/adl-keep-system-prompts-in-adl-rather-than-hardcoded-in.md 371 B
- adl/rules/adl-use-adl-alongside-mcp-tool-runtime-and-a2a.md 387 B
- adl/rules/adl-use-semantic-versioning-so-dependent-systems-can-track.md 361 B
- adl/SKILL.md 4.7 KB
- agent-skills/AGENTS.md 3.2 KB
- agent-skills/metadata.json 666 B
- agent-skills/README.md 650 B
- agent-skills/rules/_sections.md 520 B
- agent-skills/rules/_template.md 371 B
- agent-skills/rules/agent-skills-code-examples-demonstrating-correct-usage.md 328 B
- agent-skills/rules/agent-skills-concrete-guidance-the-agent-should-follow.md 316 B
- agent-skills/SKILL.md 4.0 KB
- agents-md/AGENTS.md 3.7 KB
- agents-md/metadata.json 679 B
- agents-md/README.md 630 B
- agents-md/rules/_sections.md 933 B
- agents-md/rules/_template.md 368 B
- agents-md/rules/agents-md-don-t-duplicate-readme-content.md 359 B
- agents-md/rules/agents-md-keep-it-under-150-lines.md 313 B
- agents-md/rules/agents-md-put-the-most-important-commands-build-test-at-the-top.md 383 B
- agents-md/rules/agents-md-test-your-agents.md 318 B
- agents-md/rules/agents-md-update-agents.md 281 B
- agents-md/rules/agents-md-use-directory-scoped-agents.md 333 B
- agents-md/SKILL.md 4.4 KB
- AGENTS.md 4.4 KB
- ap2/AGENTS.md 3.9 KB
- ap2/metadata.json 710 B
- ap2/README.md 645 B
- ap2/rules/_sections.md 1.1 KB
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.
- 2mo ago First seen · 76 lines · 150 tokens per session scan A 27e48afda73e
ai is a skill published in the GitHub repository Tyler-R-Kendrick/agent-skills (13 stars, last pushed 5mo ago), licensed MIT. It adds 150 tokens to every session and 1,083 once invoked, about $0.0006 per session on Opus 5.5. 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.
ai compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aiTyler-R-Kendrick/agent-skills | Skill | 13 | 5mo ago | MIT | A | 150 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |