.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/aios/_index
home/subagents/the-aios/aios/_index
the-aios avatar

_index

bythe-aios· 1 subagent

Stars

9

Forks

5

Category

AI Agents & MCP

View on GitHub

TL;DR

> Specialized task agents that spawn as sessions, execute with loaded instructions, and call close-session when done. Not persistent identities — they receive tasks, ship, report back.

How to install _index?

the-aios/aios/_index
$curl -o .claude/agents/_index.md https://raw.githubusercontent.com/the-aios/aios/HEAD/agents/_index.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install _index by running `curl -o .claude/agents/_index.md https://raw.githubusercontent.com/the-aios/aios/HEAD/agents/_index.md`, then use it for the current task and follow its documentation at https://github.com/the-aios/aios.

Files · 1

View on GitHub
agents/_index.md
1# Agents — Top-Level Registry
2 
3> Specialized task agents that spawn as sessions, execute with loaded instructions, and call close-session when done. Not persistent identities — they receive tasks, ship, report back.
4 
5Organized into **6 bundles by purpose**. Install only the bundles you need.
6 
7---
8 
9## Bundles
10 
11| Bundle | Purpose | Count |
12|---|---|---|
13| **`aios/sales/`** | Lead generation, proposals, CRM, brand monitoring | 4 |
14| **`aios/strategy/`** | Market research, advisory, company analysis, open-source governance | 4 |
15| **`aios/finance-legal/`** | Accounting, legal review, invoicing, compliance | 4 |
16| **`aios/engineering/`** | Code review, documentation, bug triage, security, building, growth, refactoring | 8 |
17| **`aios/communication/`** | Content, decks, emails, meeting prep, reports, design systems, animation | 8 |
18| **`aios/personal/`** | Study, journaling, growth, decision-making, onboarding, crisis | 6 |
19| **`custom/`** | Your own agents (operator-specific extensions, never synced) | — |
20 
21**Total bundled agents: 34.** Each bundle has a `README.md` describing its scope; this file is the master registry.
22 
23> **Standard:** all agents follow the [Agent Skills open standard](https://github.com/anthropics/skills) (138K⭐ — Anthropic's public canonical repo). Cross-platform compatible with Claude Code, Codex, Gemini CLI, Cursor, Antigravity.
24 
25---
26 
27## How agents work
28 
291. **Define:** Create an agent file from [[agent-template]] in the relevant bundle subfolder (or `custom/` for your own).
302. **Match:** `/today` reads this index, matches tasks to agents by keywords/domain.
313. **Spawn:** `spawn {name}` opens a new terminal and launches a session with the agent's instructions loaded.
324. **Execute:** Agent does the work with its specified tools.
335. **Close:** Agent calls `/close-session` — writes what it did, what's unresolved.
346. **Report:** `/close-day` picks up the session report and routes it.
35 
36---
37 
38## Agent matching
39 
40When a session starts with a name that doesn't have an exact match, the spawn wrapper + CLAUDE.md perform **glob + fuzzy matching:**
41 
421. **Exact match** → `agents/**/{name}.md` glob — first match wins. Both bundle agents and `custom/` agents resolve.
43 - Conflict rule: if two bundles ship an agent with the same name, the wrapper warns and lists matches. `custom/` always takes precedence over bundled (operator overrides).
442. **Semantic match** → scan this registry table (and `custom/_index.md` if it exists). Compare session name against agent names, purposes, domains, and match keywords. Pick the closest match if confidence is high.
45 - `bookkeeper` → matches [[accountant]] (finance domain, bookkeeping keywords)
46 - `contract-reviewer` → matches [[lawyer]] (legal domain, contract/NDA keywords)
47 - `strategist` → matches [[consultant]] (strategy domain, advisory keywords)
483. **No match** → general-purpose worker with session name as role context.
49 
50When a fuzzy match is used, the session tells the user which agent was matched and why, so they can correct if wrong.
51 
52**`archetype:` tags** (e.g. `archetype: maintainer`) mark an agent's *posture* — the [[../skills/aios/team-archetypes/SKILL|five product archetypes]] (Prototyper / Builder / Sweeper / Grower / Maintainer) — **orthogonally to its domain capability**. One agent can carry several (it shifts posture by project stage). They make *"who's my Builder / Maintainer?"* resolvable and let `/7plan` + `/emerge` check the deployed mix matches the project's lifecycle stage (not `/today` — daily routing is tactical, stage→mix is strategic). They are a *lens layered on top of* the domain bundles — never a reason to rename or restructure agents.
53 
54---
55 
56## Agent vs Session
57 
58| | Agent | Persistent session |
59|---|---|---|
60| Identity | Task-specialized, temporary | Named identity, personal |
61| Lifecycle | Spawn → execute → close-session | Runs continuously |
62| Free will | Executes assigned tasks only | Autonomous decisions |
63| Scheduling | Can be scheduled (cron/recurring) | Always-on or manual |
64| Example | lead-gen, code-reviewer, content-writer | Primary sessions (e.g. `buddai`, `sarah`) |
65 
66---
67 
68## Registry (all bundles, all agents)
69 
70<!-- /today reads this table to match tasks to agents. -->
71 
72### aios/sales/ — Lead generation, proposals, CRM, brand
73 
74| Agent | Purpose | Match keywords | Schedule |
75|---|---|---|---|
76| [[sales-lead-hunter]] | Explore leads, qualify, score, draft outreach emails | lead, prospect, outreach, qualify, pipeline, hunt | on-demand |
77| [[sales-proposal-writer]] | Draft proposals from project notes + the user's consulting catalog | proposal, quote, offer, pitch, engagement letter | on-demand |
78| [[sales-crm-updater]] | Sync deal updates to Monday/CRM from meeting notes | CRM, Monday, deal update, pipeline sync | on-demand |
79| [[brand-monitor]] | Track mentions, competitors, industry news | brand mentions, competitor check, industry news, mark

Preview

the-aios/aiosthe-aios/aios

# Agents — Top-Level Registry

> Specialized task agents that spawn as sessions, execute with loaded instructions, and call close-session when done. Not persistent identities — they receive t

Organized into **6 bundles by purpose**. Install only the bundles you need.

---

Repothe-aios/aios
TypeSubagents
CategoryAI Agents & MCP
UpdatedJul 2026
LicenseGPL-2.0
First seenJul 27, 2026

Tags

Subagent

Related

6 picks
Type
  1. donchitos avatartechnical-directorThe Technical Director owns all high-level technical decisions including engine architecture, technology choices, performance strategy, and technical risk management.SubagentsMay 202623k
  2. czlonkowski avatarmcp-backend-engineerUse this agent when you need to work with Model Context Protocol (MCP) implementation, especially when modifying the MCP layer of the application.SubagentsJul 202622k
  3. cobusgreyling avatarverifierPractical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit,…SubagentsJul 20269.5k
  4. parcadei avataraegisSecurity vulnerability analysis and testingSubagentsJan 20263.9k
  5. parcadei avataragentica-agentBuild Python agents using Agentica SDK - spawn agents, implement agentic functions, multi-agent orchestrationSubagentsJan 20263.9k
  6. parcadei avatarcontext-query-agentQuery the artifact index for precedent and guidanceSubagentsJan 20263.9k