Agentic Plugin Marketplace is a collection of reusable plugins, agents, skills, commands, and rules for coding-agent tools including Claude Code, Codex CLI, Cursor, OpenCode, Antigravity CLI, and GitHub Copilot. It is for developers assembling agentic workflows across multiple harnesses from shared Markdown sources, and the catalogue entries are examples or subsets of those workflow components.
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/wshobson/agentsWrote 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/rules/wshobson/agents/020-agent-skill-authoring)<a href="https://agentmods.dev/rules/wshobson/agents/020-agent-skill-authoring"><img src="https://agentmods.dev/badge/rules/wshobson/agents/020-agent-skill-authoring/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/rules/wshobson/agents/020-agent-skill-authoring"><img src="https://agentmods.dev/badge/rules/wshobson/agents/020-agent-skill-authoring.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 | $0.00000 | $0.00364 |
| Opus 5.5 | $0.00000 | $0.00146 |
| Sonnet 5.5 | $0.00000 | $0.00073 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
020-agent-skill-authoring 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 1mo 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.
What it actually says
Authoring portable plugin content
This content ships to Claude Code, Codex CLI, Cursor, OpenCode, the Antigravity CLI, and Pi. The adapter framework handles per-harness mechanics, but content choices affect portability.
Frontmatter
- Agents:
name,description(with "Use when…" trigger),model: opus|sonnet|haiku|inherit, optionaltools:, optionalcolor:. - Skills:
name,description. Other Anthropic SKILL.md fields are optional and respected only on Claude Code. - Commands:
description,argument-hint.
Body
- Use action verbs, not tool-name vocabulary: prefer "open the file" over "use the Read tool". The adapter rewrites a conservative set, but the unrewritten cases bleed through.
- Cap skill body at ~8 KB. Push longer reference material into
skills/<name>/references/files. Codex will hard-truncate at 8 KB anyway. - Don't name agents
default,worker, orexplorer— they collide with Codex built-ins. - Don't reference
TodoWriteas load-bearing — it doesn't exist in Codex, Cursor, Antigravity, or Pi. TheTaskspawn tool and hooks don't exist in Codex or Cursor either, but Antigravity supports both through its native equivalents (invoke_subagent/define_subagent, lifecycle hooks).
See docs/authoring.md for the full guide.
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.
- 1mo ago Changed 11400d9a0309
- 1mo ago First seen · 25 lines · 0 tokens per session scan A d2193416858e
020-agent-skill-authoring is a cursor rule published in the GitHub repository wshobson/agents (40,863 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 364 tokens. 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 cursor rules, from other repositories
100-memory-system
Comprehensive Memory System architecture for autonomous Cursor operation.
200-tasks-workflow
Task Workflow System for project implementation.
010-cursor-rules
Guidelines for creating and maintaining Cursor rules to ensure consistency and effectiveness.
search-routing
Smart Search Routing — always use QMD semantic search when available, never bypass with grep for vault content.
execute-test
Execute Katalon True Platform/TestOps tests when the input is an existing test case, manual test case list, test suite, suite collection, execution request, or "run with AI" instruction. Use when you need to create a manual test run, start Run with AI, poll AI session results, schedule automated suites, read…
claude-md
CLAUDE.md: structuring project context for Claude Code.