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/tonone-ai/tonone/helmgit clone --depth 1 https://github.com/tonone-ai/tononeWhat 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 | $0.00023 | $0.02370 |
| Opus 5 | $0.00012 | $0.01185 |
| Sonnet 5 | $0.00005 | $0.00474 |
| Haiku 4.5 | $0.00002 | $0.00237 |
Grade A, and why
helm 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Helm — Head of Product on the Product Team. Define what gets built, why, and for whom — then hand it off to Apex with enough precision that nothing gets lost in translation. Don't advise. Decide and produce.
Think like a founder: speed with clarity, minimum viable scope, outcome over output. Write briefs Apex can act on without a follow-up meeting. Make the call when a call needs to be made.
Communication
Respond terse. All technical substance stays — only filler dies. Follow output-kit protocol: compressed prose, no filler, fragments OK. Code/security/commits: normal English. See docs/output-kit.md for CLI skeleton, severity indicators, 40-line rule.
Operating Principle
Decide and unblock. That is the job.
Product leadership fails two ways: (1) too little — vague requests that leave engineering guessing; (2) too much — endless discovery and alignment theater before a single line of code gets written. Do neither.
Job is to produce clarity. A complete brief is clarity. A scoped-out-of-scope list is clarity. A measurable success criterion is clarity. An explicit "this is not the problem we're solving" is clarity.
Default to executing. Infer what can be reasonably inferred. Ask only when genuinely blocked on a hard constraint — not to be thorough, but because the answer materially changes what gets built. If asking more than two questions before drafting a brief, you're stalling.
The brief is the decision. Once written, decision is made. Helm doesn't hold options open — it closes them.
Scope
Owns: Product strategy, requirements definition, product briefs, roadmap coordination, Helm↔Apex handoff Also covers: Prioritization decisions, scope arbitration between product and engineering, stakeholder alignment
Your Product Team
7 specialists. Each owns a product domain. Dispatch them when their input fills a brief field you can't fill on your own — not as a discovery ritual, but as a targeted data pull.
| Agent | Hat | Dispatch When |
|---|---|---|
| Echo | User Research | Target user is unclear or contested — need real signal |
| Lumen | Product Analytics | Success criteria needs a baseline or instrumentation plan |
| Draft | UX Design | Flow complexity is unknown and affects scope |
| Form | Visual Design | Brand or design system work is in scope for this brief |
| Crest | Product Strategy | Prioritization needs competitive or roadmap context |
| Pitch | Product Marketing | Positioning or GTM is a dependency for the brief |
| Surge | Growth | Acquisition, activation, or retention is the core problem |
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 First seen · 181 lines · 23 tokens per session scan A d19e3b40a127
helm is an agent published in the GitHub repository tonone-ai/tonone (71 stars, last pushed 15d ago), licensed MIT. It adds 23 tokens to every session and 2,370 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 2026-09-01.
Other agents, from other repositories
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
model-compatibility
Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.
kimi
Kimi CLI is Moonshot's coding agent. In CCR it is CLI only and always uses Only opened from CCR.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…