Building agents

38,442 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

thinking-log

6146

mduongvandinh/claude-thinking-log-plugin

Plugin Claude Code

Bundles 1 skill, 1 command · 101 tokens together

Automatically creates and maintains THINKINGLOG.md files that document Claude's reasoning process, decisions, and problem-solving approach during implementation tasks. Includes Mermaid diagrams for visualization.

not rated 2 8mo ago A tokens not measured original MIT

claude-in-claude

6147

jaidhyani/jai-cc-plugins

Plugin Claude Code

Bundles 1 skill · 112 tokens together

Programmatic Claude Code CLI testing — structured JSON output parsing, multiturn session management via --resume, and isolation patterns for CI/containers.

not rated 2 18d ago A tokens not measured

rh

6151

thaleslaray/plugins

Plugin Claude Code

Bundles 1 skill · 212 tokens together

RH automatizado scorecard-first. /rh:contratar infere scorecard cruzando cargo + .claude/agents/ + inventário local + prompt, descobre candidatos em paralelo (GitHub canonical + registries + skills.sh com install counts + MCPs), pre-curação com rubrica scoring + recomendação ÚNICA ao fundador, pesquisa externa SÓ nos…

not rated 2 4mo ago A tokens not measured original MIT

skills

6154

agentalabs/agenta-plugin

Skill Claude CodeCodex

Single source of truth for all available skills — internal and external (submodule-based).

not rated 2 5mo ago A 0 tokens original MIT

skill-review

6157

jhoblitt/skill-review-claude

Plugin Claude Code

Bundles 1 skill, 4 agents · 403 tokens together

Four-axis review gate for Claude Code skill, agent, and plugin prose — drift, concurrency, token usage, and security — enforcing the one-normative-home, shape-matches-the-work, cheapest-sufficient-mechanism, and data-carries-no-authority rules across a pre-PR instruction diff or a whole repo.

not rated 2 1mo ago A tokens not measured original Apache-2.0

fw

6158

hl/mp

Plugin Claude Code

Bundles 2 skills, 6 commands, 6 agents · 2,328 tokens together

Spec-driven workflow plugin. Brainstorm, write specs, review implementations, and compound solutions.

not rated 2 4mo ago A tokens not measured

Intellegam/agent-plugins

Skill Claude CodeCodex

How to consult Claude Code as a second-opinion agent via the claude-agent MCP tools (claude, claude-reply, claude-result, claude-cancel). Use before brainstorming with Claude (aliases @claude, @claude-code), validating a plan, requesting an external code review, or any claude-agent tool call. Form your own analysis…

not rated 2 changed 12d ago A 113 tokens

genius

6161

chenpg2/genius-plugin

Plugin Claude Code

Bundles 4 skills, 4 commands · 285 tokens together

GENIUS (Grounded Evolutionary Novelty for Ideation, Understanding & Science) — the bridge from a scientific problem to an openevolve run: Claude+Codex+Kimi debate an idea (or a local sub-problem in an existing project) into grounded, novel, computable candidates, then a human freeze-gate hands a ready evolve-dir to…

not rated 2 2mo ago A tokens not measured

Command Development

6162

BrainDAO/iq-claude-config

Skill Claude Code

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash…

not rated 2 2mo ago A 99 tokens

agent-skill-creator

6163

jetsons-zz/eos3-plugins

Skill Claude CodeCodex

This enhanced skill should be used when the user asks to create an agent, automate a repetitive workflow, create a custom skill, or needs advanced agent creation capabilities. Activates with phrases like every day, daily I have to, I need to repeat, create agent for, automate workflow, create skill for, need to…

not rated 2 9mo ago A 126 tokens

side-quest

6164

trtmn/agent-plugins

Plugin Claude Code

Bundles 1 skill, 2 commands, 1 agent · 293 tokens together

Launch background subagent(s) to handle a task as a side quest while the main conversation stays free. Use when the user types /side-quest or asks to run a task as a side quest. Rates the task's difficulty (Challenge Rating) to pick the model — haiku for trivial quests, sonnet for standard quests, opus for boss fights.

not rated 2 23d ago A tokens not measured original Unlicense

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: