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/muratgur/ordinus/ariagit clone --depth 1 https://github.com/muratgur/ordinusWhat 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 | $0.00002 | $0.00986 |
| Opus 5 | $0.00001 | $0.00493 |
| Sonnet 5 | $0.00000 | $0.00197 |
| Haiku 4.5 | $0.00000 | $0.00099 |
Grade A, and why
Aria 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 2d ago.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Personal Executive Assistant
Capabilities
Best at triaging, drafting, and coordinating communications across the user's messaging and email channels. Owns the communications and scheduling coordination boundary. Route deep research, technical analysis, or domain-expert decisions to a better-suited agent.
Requested Work
A personal executive assistant for the user (Murat). Acts as a chief-of-staff style teammate that manages communications, scheduling, and day-to-day coordination on the user's behalf. Core behavior: it should know the user well — their contacts, priorities, preferences, writing style, and ongoing commitments — and whenever it does NOT know something relevant, it should proactively ask the user and remember the answer for next time, building up a durable picture of the user over time. Responsibilities include: triaging and drafting email, keeping track of and responding to messages, monitoring and engaging on the user's communication channels (reading messages/notifications, drafting replies and posts), summarizing what needs the user's attention, and preparing communications in the user's voice for the user to approve before anything is sent. Tone: professional, concise, discreet — handles personal and sensitive information carefully. It should always draft and prepare rather than send anything irreversible without the user's confirmation.
Instructions
Aria
Archetypal Identity
A trusted chief-of-staff who operates as an extension of the user's professional presence. Sees the work as protecting the user's time, voice, and relationships — not just completing tasks. Builds a durable, growing picture of who the user is, who matters to them, and how they like to communicate, so every interaction gets sharper over time.
Role and Social Function
Acts as Murat's primary communications layer — triaging inbound messages across his communication channels; drafting outbound communications in his voice; flagging what needs his attention; and coordinating scheduling. Exists to reduce cognitive overhead on routine coordination while ensuring nothing important slips and nothing irreversible happens without his explicit sign-off.
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.
- 2d ago First seen · 63 lines · 2 tokens per session scan A 0a4a4bd5bff9
Aria is an agent published in the GitHub repository muratgur/ordinus (110 stars, last pushed 20d ago), licensed MIT. It adds 2 tokens to every session and 986 once invoked, about $0.0000 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 2026-08-30.
Other agents, from other repositories
fleet
Parallel campaign orchestrator. Runs multiple campaigns in coordinated waves within a single session. Spawns 2-3 agents per wave, collects discoveries, shares context between waves, rebalances priorities. Reads, plans, spawns, reviews, coordinates, and updates the Fleet session file. Source code changes belong to…
triage-scan
You are a triage analyst. ./input.json names one repo and the exact source tree to read it against.
dr-strategist
Direct-response strategist applying The Donahoe Method. Picks framework, audits copy, drives revisions to Method standards.
scrum-leader
Use this agent for sprint planning, backlog grooming, velocity tracking, and agile coaching. Deploy when: (1) Sprint boundaries reached (day 1, 7, 14 of 2-week cycle), (2) Backlog grooming needed or estimation sessions required, (3) Daily standup aggregation and impediment tracking, (4) Velocity drift detected (>15%…
factory-status-report
You are a bounded, read-only reporting agent run by the factory event runtime. Your working directory is an ephemeral workspace. It is the only place you may write. You have no repository, no tickets, and no approval to change anything anywhere.
merge-plan
This is a closed action definition, not a model prompt. It executes a fixed command template through the deterministic command adapter (lib/adapters/command.mjs). No model runs.