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/rimio-ai/rimz/modelgit clone --depth 1 https://github.com/rimio-ai/rimzWrote 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/rimio-ai/rimz/model)<a href="https://agentmods.dev/agents/rimio-ai/rimz/model"><img src="https://agentmods.dev/badge/agents/rimio-ai/rimz/model.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 | $0.00000 | $0.11610 |
| Opus 5 | $0.00000 | $0.05805 |
| Sonnet 5 | $0.00000 | $0.02322 |
| Haiku 4.5 | $0.00000 | $0.01161 |
Grade A, and why
model 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 today.
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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The agent model
A coding agent runs in a pane, reports through its own hooks, and appears in the sidebar as one card. This doc owns the model in between: how a native event becomes one durable state per agent, how that state moves, and how the row you see is projected from it.
The pipeline has three stages, each owned by a different doc:
adapter ── produces ──► AgentLifecycleObservation (one per native event) adapter.md
this doc ── folds ────► AgentState (one per agent) model.md
sidebar ── projects ──► a sidebar row sidebar.md
An adapter produces an AgentLifecycleObservation from each native event (adapter.md); this doc folds those observations into one AgentState per agent; sidebar.md projects that state into a row. The observation is agent-agnostic by construction, so everything below is too: a new agent that emits well-formed observations gets the state machine, ranking, liveness, and attention routing for free.
The commitments this operationalizes are in DESIGN.md. Which native event means what for each agent is that agent's own page (adapter_claude.md, adapter_codex.md, and eleven siblings); the account, balance, spend, and pricing model is providers.md.
Four nouns
- An agent kind is a wired integration (
claude,codex,amp,copilot,kimi,pi,opencode,antigravity,cursor,droid,kiro,qwen,grok), described by anAgentSpec. - An agent instance is presence: a live local pane running a known agent right now, read from the multiplexer every tick.
- A session is identity: the id the agent's own hooks report, keyed
(kind, agent_id), where every durable fact attaches. - The rollup entry is the one
AgentStateper session that store replay derives: the durable record the sidebar enriches and renders.
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.
- today Changed · +2 lines 4c7a2b2458f7
- 4d ago First seen · 334 lines · 0 tokens per session scan A 81232df3ce60
model is an agent published in the GitHub repository rimio-ai/rimz (23 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 11,610 tokens. 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
executor
Executes plan tasks with atomic commits, deviation handling, checkpoint protocols, TDD support, and self-verification.
planner
Creates executable phase plans with task breakdown, dependency analysis, wave assignment, and goal-backward verification. Also creates roadmaps.
verifier
Goal-backward phase verification. Checks codebase reality against phase goals - existence, substantiveness, and wiring of all deliverables.
debugger
Systematic debugging using scientific method. Persistent debug sessions with hypothesis testing, evidence tracking, and checkpoint support.
plan-checker
Verifies plans will achieve phase goals before execution. Goal-backward analysis of plan quality across 10 dimensions.
researcher
Unified research agent for project domains, phase implementation approaches, and synthesis. Follows source-hierarchy methodology with confidence levels.