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/plugingit clone --depth 1 https://github.com/rimio-ai/rimzWhat 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 | $0.00812 |
| Opus 5 | $0.00000 | $0.00406 |
| Sonnet 5 | $0.00000 | $0.00162 |
| Haiku 4.5 | $0.00000 | $0.00081 |
Grade A, and why
plugin 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent plugin internals
agents/adapters/plugin/ turns machine-tier bundle manifests into process-lifetime AgentDefinition values. The process boundary is the runtime: agent-owned shims push canonical hook JSON, and optional short-lived executables pull spend, account, and version enrichment.
Load and registry
load.rs scans $XDG_CONFIG_HOME/rimz/agents.d/*/agent.toml, sorts paths for deterministic display order, validates collisions and bundle paths, and caches the result in a OnceLock. It returns valid adapters, structured load errors, and doctor diagnostics in one pass.
registry.rs keeps the built-in BUILTINS slice for built-in hook management and exposes all_definitions() for kind resolution, coverage, doctor, presence, launches, and spend discovery. A valid plugin therefore reaches the lifecycle reducer, sidebar, target resolver, layout grammar, messaging, and provider dashboard through the existing adapter seam.
Definition capability objects use &'static references. Loading leaks each validated manifest, spec, adapter, and derived table once for the process lifetime. The allocation is bounded by machine configuration; live manifest reload is the threshold for replacing it with owned shared registry values.
Derived declarations
manifest.rs makes emits the source of truth for native lifecycle coverage. PluginAdapter derives every IntegrationConcern and LifecycleSignalKind row from emitted-event declarations, capabilities, and probe presence, so a plugin author cannot hand-write a greener matrix than the bundle implements.
The spec owns leaked strings for branding, tools, process names, activity events, setup guidance, and launch facts. Hook installation remains self-managed and points at setup-doc; undeclared capabilities stay absent.
Ingest and probes
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 · 32 lines · 0 tokens per session scan A 51e97385f419
plugin is an agent published in the GitHub repository rimio-ai/rimz (23 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 812 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
default-workflow
The order of work for any task: what to read first, how to scope a change, how to verify, and how to commit and open pull requests. Topic-specific rules live in the pages linked under References.
maintaining-agent-docs
Agent "maintaining-agent-docs" from martin-francois/symphony-trello, covering maintaining agent docs, progressive disclosure contract, what may be added to agents.md (allowlist), what must not be added to agents.md (denylist) and where to put new guidance (decision tree).
progressive-disclosure-source
This file is the source of truth for the structure and maintenance approach.
java-style
How to write and shape Java code in this repository: formatting, language-feature use, complexity and reuse tradeoffs, and exception handling. Static-analysis tooling has its own page; see References.
github-issue-triage
How to run issue triage sweeps, manage issue dependencies, and apply triage labels. Spec-alignment auditing that may create issues lives in Specification & ADR discipline.
testing
How to write unit and integration tests in this repository, including frameworks, structure, and parallel safety. Live end-to-end and deployed-verification rules live in Deployment & live verification. How to run the build is in Default workflow.