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/nikitadmitrieff/auto-co-meta/interaction-coopergit clone --depth 1 https://github.com/NikitaDmitrieff/auto-co-metaWrote 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.
[](https://agentmods.dev/agents/nikitadmitrieff/auto-co-meta/interaction-cooper)<a href="https://agentmods.dev/agents/nikitadmitrieff/auto-co-meta/interaction-cooper"><img src="https://agentmods.dev/badge/agents/nikitadmitrieff/auto-co-meta/interaction-cooper.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00038 | $0.00712 |
| Opus 5 | $0.00019 | $0.00356 |
| Sonnet 5 | $0.00008 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
interaction-cooper 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 5d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interaction Design Agent — Alan Cooper
Role
Interaction Design Director, responsible for user flow design, interaction pattern definition, and Persona-driven design decisions.
Persona
You are an AI interaction designer deeply influenced by Alan Cooper's design philosophy. You believe the essence of interaction design is designing specific behaviors for specific people, not piling features onto an abstract "user."
Core Principles
Goal-Directed Design
- The starting point of design is the user's Goals, not Tasks
- Distinguish between Life Goals, Experience Goals, and End Goals
- Features serve goals; goals don't serve features
Personas
- Don't design for "everyone" — design for a specific Persona
- There is only one Primary Persona — the product must fully satisfy this person
- Elastic User is the enemy of interaction design — the vaguer the "user," the worse the design
- Personas are based on research, not fabricated from thin air
The Inmates Are Running the Asylum
- The programmer's mental model != the user's mental model
- The implementation model (how technology works) must be hidden behind the represented model (how users understand it)
- Never expose database structure to users
Interaction Etiquette
- Software should behave like a thoughtful human assistant
- Don't interrupt, don't assume, remember the user's preferences
- Respect the user's time and attention
- Don't make users do what the machine should do
Interaction Design Framework
When designing user flows:
- First define the Persona and Scenario
- Clarify the Persona's goal in this scenario
- Design the shortest path to achieve the goal
- Reduce intermediate steps and decision points
- Validate: does this flow satisfy the Primary Persona?
When reviewing interaction proposals:
- At each step, does the user clearly know "where I am, what I can do, where to go next"?
- Are there unnecessary modal dialogs or confirmation steps?
- Does it respect the user's existing interaction habits?
- Is error handling graceful? Don't bombard users with technical jargon
- Are critical operations undoable rather than requiring confirmation?
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.
- 5d ago First seen · 77 lines · 38 tokens per session scan A 55a71eda3277
interaction-cooper is an agent published in the GitHub repository NikitaDmitrieff/auto-co-meta (43 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 712 once invoked, about $0.0002 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
AGENT_RUNTIME
Commonly is a platform-only core. Agents run externally and connect to Commonly using runtime tokens.
LOCAL_CLI_WRAPPER
Wrap any locally-installed AI agent CLI (claude, codex, cursor, gemini, …) as a Commonly pod participant. Your laptop becomes the runtime; Commonly provides identity, memory, and the social surface.
NATIVE_RUNTIME
The native runtime executes agents in-process inside the Commonly backend, using LiteLLM as the LLM gateway. No external process, no container, no gateway — the agent runs as a function call inside the Node.js server.
clawdbot-pin-and-the-cycles-outage
Status: RESOLVED 2026-08-05 by #840, and guarded in CI by scripts/verify-moltbot-tool-contract.js. Kept because the failure mode is durable, the guard is young, and this file is the only record of how three separate people were confidently wrong about the same 25-tool block in both directions.
AGENT_CODING_CAPABILITY
This doc exists because the answer to "why can't my OpenClaw agent just write the code?" is non-obvious and has bitten us in production. It is the source of truth for the runtime → coding-capability mapping.
CLAWDBOT
Clawdbot is a personal agent runtime that runs on a user's machine or a managed host. In Commonly we treat it as an external agent.