An MCP connection to AIWorkers, a service for managing automated workers, chats, memory, tasks, surveys, Telegram commands, and account or group balances. It includes a login flow that keeps tokens out of URLs and chat.

Managing AIWorkers, including workers, chats, saved replies, surveys, tasks, Telegram workers, balances, salary quotes, and one-time TokenTime purchases.

It gives the coding agent access to AIWorkers operations without requiring credentials in configuration links or conversations. It also provides guidance for installing, logging in, checking the account, and updating the connection.

aiworkers — Skill for Claude Code and Codex by dimaneuron

Install

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.

Any agent

npx skills add dimaneuron/aiworkers-mcp --skill aiworkers_mcp

Clone the repo

git clone --depth 1 https://github.com/dimaneuron/aiworkers-mcp

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dimaneuron/aiworkers-mcp/aiworkers_mcp/github.svg)](https://agentmods.dev/skills/dimaneuron/aiworkers-mcp/aiworkers_mcp)

Your own site

<a href="https://agentmods.dev/skills/dimaneuron/aiworkers-mcp/aiworkers_mcp"><img src="https://agentmods.dev/badge/skills/dimaneuron/aiworkers-mcp/aiworkers_mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dimaneuron/aiworkers-mcp/aiworkers_mcp"><img src="https://agentmods.dev/badge/skills/dimaneuron/aiworkers-mcp/aiworkers_mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 227 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,838 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00227	$0.05838
Opus 5.5	$0.00091	$0.02335
Sonnet 5.5	$0.00045	$0.01168
Haiku 4.5	$0.00023	$0.00584

Measured 4d ago against content hash 9c57720bcbdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

aiworkers scanned grade B with 1 finding 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 4d ago.

The scan reads SKILL.md. This mod also ships 20 executable files (__init__.py, __main__.py, http.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

3. Human runs `aiworkers-mcp login`: it prints a code + Telegram link, they tap **Confirm** in the Mini App, and the CLI writes `~/.config/aiworkers/credentials.json` (`chmod 600`) by itself (device pairing, default). Fa

aiworkers_mcp/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AIWorkers MCP

Thin MCP client. Business logic stays on https://ai.knopka.click. Do not invent tokens or seeds.

Install docs (source of truth): https://github.com/dimaneuron/aiworkers-mcp
Landing: https://ai.knopka.click/mcp
Product: https://ai.knopka.click

If this project has no MCP yet: read that README, install aiworkers-mcp, have the human run aiworkers-mcp login, then aiworkers_whoami and aiworkers_skill_update.

Call aiworkers_login_link (works without a key) and give the human this URL: https://t.me/aiworkersbot?start=mcp
They open it in Telegram, create a parent token in the Mini App (wallet creation itself issues none; they can create many and revoke each; it is shown once). Seed of 12 words never goes to chat or to the server.
Human runs aiworkers-mcp login: it prints a code + Telegram link, they tap Confirm in the Mini App, and the CLI writes ~/.config/aiworkers/credentials.json (chmod 600) by itself (device pairing, default). Fallback: aiworkers-mcp login --paste (also offered on Ctrl+C / expiry / pairing failure) and paste the one-time token from step 2; this also takes awm_ module tokens.
Restart the agent. Call aiworkers_whoami.

Do not put tokens in git, in mcp.json committed to the repo, or in chat. Prefer aiworkers-mcp login over env in config.

Device-code login (no copy-paste)

Alternative to steps 1-3 above: call aiworkers_login_start — no key required. It returns a short user_code and a verify_url (https://t.me/aiworkersbot?start=mcplogin_<code>). Tell the human to open that link and tap Confirm inside the Mini App; this still needs their 12-word wallet (or an existing unlocked device session) — a bare bot-button tap is not enough. Then call aiworkers_login_poll (retry while status is "pending"). On "confirmed" the new parent awp_ token is written straight to credentials.json by the tool code itself — it is never shown in chat or returned to the model. This mints an independent additional parent token: it does not revoke any other device's/agent's already-issued token, so several agents can each hold their own live session. Restart the agent afterward so the new token is picked up.

Read the full file on GitHub · 143 lines

Files

What ships with it

20 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.

Changes

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.

4d ago Changed 9c57720bcbdd
7d ago Changed · +2 lines c080fef0bcf1
16d ago Changed a10c886c1f44
18d ago Changed · +5 lines 43ba0670414c
1mo ago First seen · 136 lines · 227 tokens per session scan B 4e2c7e50ac56

Subscribe to this mod's changes

aiworkers is a skill published in the GitHub repository dimaneuron/aiworkers-mcp (0 stars, last pushed 6d ago), licensed MIT. It adds 227 tokens to every session and 5,838 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Memory and context

mem0-oss-to-platform

Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…

mem0ai/mem0 · 217 tokens

forget

Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…

asgeirtj/system_prompts_leaks · 74 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens

aiworkers