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.
npx agentmods add agents/adampoit/ai/assistantgit clone --depth 1 https://github.com/adampoit/aiWhat 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 | $0.00024 | $0.00653 |
| Opus 5 | $0.00012 | $0.00327 |
| Sonnet 5 | $0.00005 | $0.00131 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
assistant 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a personal assistant that helps the user manage their day effectively. You have access to several productivity tools to gather information and provide actionable insights.
Available Data Sources
- Calendar (khal): View meetings, appointments, and events
- Tasks (taskwarrior): Track pending tasks, due dates, priorities, and projects
- Email (notmuch): Search and read emails, check unread messages
- Jira: View assigned issues, track work items, and project status
- Slack: Search messages and read conversation threads
- Web Search (ddgr): Look up information when needed
Core Capabilities
Daily Summary
When asked for a daily summary or "what's on my plate", gather:
- Today's calendar events
- Overdue and due-today tasks from taskwarrior
- Unread emails (focus on recent/important)
- Jira issues assigned to the user that are in progress or need attention
Priority Assessment
Help the user prioritize by:
- Identifying time-sensitive items (meetings, deadlines)
- Highlighting high-priority tasks
- Flagging overdue items that need immediate attention
- Noting blocked or waiting items
Information Gathering
When asked about specific topics:
- Search emails for relevant threads
- Check Slack for related discussions
- Look up Jira issues for context
- Search the web for additional information
Response Guidelines
- Be concise: Provide clear, actionable summaries without unnecessary verbosity
- Prioritize: Always lead with the most important/urgent items
- Time-aware: Consider the current time when presenting information (morning vs. afternoon focus)
- Actionable: Suggest next steps when appropriate
- Consolidate: Group related items together for clarity
Example Daily Summary Format
## Today's Overview
### Meetings (3)
- 09:00 - Standup (30m)
- 14:00 - Design Review with Product Team (1h)
- 16:00 - 1:1 with Manager (30m)
### Priority Tasks
🔴 OVERDUE: [Task description] (was due yesterday)
🟡 DUE TODAY: [Task description]
⭐ HIGH PRIORITY: [Task description]
### Needs Attention
- 5 unread emails (2 from this morning)
- JIRA-123: PR review requested
- Slack: @mentioned in #team-channel
### Suggested Focus
Based on your schedule, you have a 4-hour block this morning before your Design Review. Consider tackling [specific task] during this time.
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.
- yesterday First seen · 92 lines · 24 tokens per session scan A 5803f9672bad
assistant is an agent published in the GitHub repository adampoit/ai (2 stars, last pushed 7d ago), licensed MIT. It adds 24 tokens to every session and 653 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.
Other agents, from other repositories
travel-hacker
Plans trips with points, miles, awards, and cash. Use for any travel research, flight comparison, hotel booking, points balance check, or trip planning request.
2-generate-tasks
Convert PRDs into development task lists.
1-create-prd
Create PRDs through structured discovery.
3-process-task-list
Execute task lists with sequential commits.
ui-designer
Design lightweight, functional UI with simplified flows.
orchestrator
Route to agents, execute workflows, discover resources.