rea
01Plugin Claude Code
Bundles 5 skills, 1 MCP server · 245 tokens together
Reverse engineer anything with agents, from app behavior down to native binaries.
not rated 439k
+19k
changed 9d ago A
tokens not measured
original MIT
632,734 ▼ 180,667 this week
Mods indexed, across nine kinds and every major agent
147,212 ▲ 124 this week
Repositories crawled, each re-checked and re-hashed
25,489 ▲ 272 this week
Plugins and marketplaces, wrapping 228,834 mods between them
70,155 ▲ 364 this week
Copies and forks identified, linked to their originals and demoted
Or by subject
Browse by category
Every mod is filed by what it actually does — read and judged one at a time, not matched on keywords. Each category opens the full list; the Top menu holds the measured hundred.
Claude Code81,700Building agents40,662Planning37,290Research28,028Security27,012Analytics and metrics25,074Writing and docs25,040DevOps and cloud22,741Creative and media21,674Marketing and SEO21,645Frontend20,604Project management20,185Testing20,047Backend and APIs19,626Code review19,429Design and UX19,074Debugging17,014Scientific16,362Finance and fintech16,293Git and workflow15,525Languages15,070Data and AI14,178Productivity14,063Memory and context12,533Documents12,152Legal and compliance9,712Databases9,512Learning and teaching8,654Browser automation7,477Game development6,969Mobile6,607E-commerce6,400Web3 and blockchain5,374Hardware and IoT5,203Localization1,914
Browse
Nine kinds of mod, one catalogue
They are all the same shape of thing: a file you drop in that changes how the agent behaves. Splitting them across nine sites is what everyone else does, and it is why nobody can tell you what your whole stack costs.
277,983
Skills
Loaded on demand. Two digits per session until invoked.
25,078Agents
Subagents with their own prompt. Injected whole.
28,277Commands
Slash commands, one file per job.
56,172MCP servers
Servers. The cost is their tool schemas, not the config.
23,873Cursor rules
Cursor rules, loaded whole into a matching conversation.
193Instructions
AGENTS.md, CLAUDE.md, copilot-instructions.
1,240Hooks
Shell commands your agent runs. Read before installing.
91Settings
Configuration, so you can see what others turn on.
23,569Plugins
Bundles of the above, shipped together.
Stars this week
Moved this week
The six mods whose repositories gained the most stars in the last seven days — movement, not accumulated fame.
Skill Claude CodeCodex needs its repo
Bring up a new Alchemy cloud provider (its own @alchemy.run/ package under packages/ ) end to end — credentials, a distilled SDK, resources, bindings, live tests, and the patch loop that feeds live-test failures back into distilled — or extend an existing provider with a new service, or bring an existing provider up…
not rated 50k
+12k today A 153 tokens
original MIT
Skill Claude CodeCodex
Scrape web pages using Scrapling with HTTP requests, stealth browsers, JavaScript rendering, browser actions, API response capture, concurrent spiders, and adaptive parsing. Use when asked to scrape, crawl, or extract data from websites; webfetch fails; the site has anti-bot protections; write Python code to…
not rated 99k
+6.8k
changed 2d ago A ✓ AI review SkillSpector: warn 76 tokens
original BSD-3-Clause
Plugin Claude Code
Bundles 38 skills · 1,293 tokens together
Matt Pocock's agent skills for real engineering: grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
not rated 317k
+6.6k
changed 8d ago A ✓ AI review
tokens not measured
original MIT
Skill Claude CodeCodex ✓ vendor
Use on Windows for unexpected DSH sandbox access denials: workspace writes or listing fail, or an ordinarily readable path cannot be read. One bundled command inspects the path and every ancestor and repairs the ACL problems it proves in that same run. Expected confinement denials need no ACL repair.
not rated 275k
+6.2k
changed 1mo ago A 67 tokens
original MIT
cloudflare/security-audit-skill
Skill Claude CodeCodex ✓ vendor
Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons. Use for security questions, focused reviews, vulnerability research, security audits, or pen tests. Run the complete workflow only for explicit codebase audit or pen-test requests, full/comprehensive/end-to-end…
not rated 65k
+6.0k
changed 1mo ago A Socket: passSnyk: warnSkillSpector: pass 72 tokens
original MIT
Fewest tokens
Cheapest of what’s moving
Mods people are picking up this week, sorted by what they add to every session before you have asked anything. No other catalogue can offer this sort, because no other catalogue counts.
galyarderlabs/galyarder-framework
Cursor rule Cursor
The local environment is optimized with rtk (Rust Token Killer). Always use the rtk prefix for shell commands (e.g., rtk npm test) to minimize token consumption.
not rated 29
+1 27d ago C 1 tokens
original MIT
news
02Skill Claude CodeCodex
You have a newsfetch tool that fetches raw news headlines and article content from multiple sources (Google News RSS, Hacker News API, Yahoo News, Substack, Medium). Use it to build daily news digests for the user.
not rated 766
+1 today A SkillSpector: pass 1 tokens
original Apache-2.0
news
03Skill Claude CodeCodex
Glance at one fresh headline and drop it into a single sentence in your own words — a casual, half-distracted aside between songs, never an anchor or newsreader voice, never the headline read verbatim, no editorialising, no "in other news". Steer to the lighter, cultural, or human-interest item; if everything on the…
not rated 1.6k
+59 today A SkillSpector: pass 1 tokens
original MIT
wps
04Orkas-AI/Orkas-Awesome-AgentSkills
Skill Claude CodeCodex
Use when the user explicitly mentions WPS, WPS Office, WPS Writer, WPS Spreadsheets, WPS Presentation, Chinese office formatting, WPS-to-Office compatibility, print setup, or PDF export from WPS.
not rated 15
+1 4mo ago A 1 tokens
original MIT
wps
05Skill Claude CodeCodex
Use office-word, office-excel, or office-ppt for the artifact-specific workflow, and apply the WPS compatibility checks in this skill.
not rated 9.1k
+2.7k
changed 1mo ago A SkillSpector: pass 1 tokens
original MIT
subscription
06Skill Claude CodeCodex
Allow a viewer to subscribe to this agent for recurring USDC payments. The agent charges 5 USDC per week automatically — no re-signing needed — until the viewer revokes or the delegation expires (90 days).
not rated 269
+7 today A SkillSpector: pass 1 tokens
original Apache-2.0
The four measurements
What a listing does not tell you
Every catalogue shows that a mod exists and how many stars sit behind it. None of them tells you what it costs, whether it is safe, whether it is the original, or whether it changed under you.
What it costs, in tokens
Per session and once invoked, counted locally with o200k_base and priced per model. A stack of six agents is twenty thousand tokens before you have typed anything.
skills: 52 tokens average, preloaded
agents: 1 718, every session
agents: 1 718, every session
A scan with its reasons
Hidden Unicode, instruction-override phrasing, curl piped into a shell, recursive deletes, credential paths. A grade from A to F, and the exact line behind every finding.
not a badge: the matched line
scan, not verified
scan, not verified
Original, or one of the copies
Bodies are simhashed and clustered. The one with the most behind it is the original; the rest say how identical they are and point at it instead of competing with it.
indexed: everything
shown: the ones that differ
shown: the ones that differ
What changed since last week
Hashed on every crawl, with the history kept rather than the latest state alone. A supply-chain change to an agent config is a question of when, not whether.
every version: hash + date
Stars do not decide the order
Stars belong to the repository, not the mod: one repo with 170k stars and 139 skills would own the first three pages. Reputation enters through log10 and carries a quarter of the weight.
reputation 25 · freshness 20 · safety 20
originality 15 · quality 10 · traction 10
originality 15 · quality 10 · traction 10
Nothing is hosted here
Every mod stays where its author put it and every page links to the source file. Bodies appear only under a permissive licence we can name; no LICENSE means all rights reserved, an unidentifiable one means unknown terms, and those pages say which.
we index. authors publish.
FAQ Frequently
Frequently
asked questions
What a mod is, what the numbers mean, and what this catalogue does and does not do.
agentmods, one word, at agentmods.dev, is a catalogue of mods for coding agents: skills, subagents, commands, hooks, rules, instructions files, MCP servers and plugins for Claude Code, Cursor, Codex and Copilot. Every entry is measured rather than merely listed: what it costs in tokens per session, what a security scan found and why, whether it is the original or a copy, and what changed since last week. The same data is on the command line as npx agentmods.
Anything you add to a coding agent to change how it behaves: a skill, a subagent, a slash command, a hook, a Cursor rule, an instructions file, an MCP server, a plugin bundle. They are all the same shape of thing — a file you drop in that the agent then reads — so they belong in one catalogue rather than nine.
Because a mod is not free to have installed. An agent or a Cursor rule is injected into the context of every session whether or not you use it, and a stack of them can be twenty thousand tokens before you have asked anything. Every page here prints what the mod costs per session and what it costs once invoked, counted locally with the o200k_base tokenizer.
It is a static scan, not an audit, and the page says so. It looks for hidden Unicode, instruction-override phrasing, shell pipes into a downloaded script, recursive deletes, privilege escalation, credential paths and encoded payloads. Every finding is printed with the line that produced it, so you can judge whether it matters in context rather than trusting a letter.
Because most of them are. Bodies are simhashed and near-identical documents are clustered; the one with the most behind it is treated as the original and the rest point at it. A catalogue that lists nine copies of the same skill as nine results is making the search harder, not easier.
No. Every mod stays where its author put it, and every page links to the source file. Bodies are shown only where the repository carries a permissive licence we can name. No LICENSE means all rights reserved, and a LICENSE we cannot identify means terms we will not guess at; either way those pages carry the metadata, the measurements and a link.
Mod your agent
Find the one you need, and know what it costs
632,734 mods, measured four ways. Search by name, or sort a whole category by what it adds to your context.