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 skills add javded-itres/Holix --skill typed-decisiongit clone --depth 1 https://github.com/javded-itres/HolixWrote 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/skills/javded-itres/holix/typed-decision)<a href="https://agentmods.dev/skills/javded-itres/holix/typed-decision"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/typed-decision/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/javded-itres/holix/typed-decision"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/typed-decision.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00036 | $0.00381 |
| Opus 5.5 | $0.00014 | $0.00152 |
| Sonnet 5.5 | $0.00007 | $0.00076 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
typed-decision 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 10d 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.
What it actually says
When to use
Call systemone_decide only for a judgment with answers you already listed:
- one label from a fixed set (
choice) - a position on a scale you wrote, worst to best (
score) - whether one statement is true (
noul)
The default decision model is multilingual. Write state and criteria in the same language as the user. Do not translate them to English first.
Do not use it to draft a reply, write code, extract a free string (a name, a sum, a paragraph), or search memory.
Call
state is the text or object to judge. questions is a map. The question id is only a label. The meaning belongs in instructions and criteria.
choice:criteriais an object of allowed answer to when it applies.score:criteriais an array of at least two levels, lowest to highest. The score is a position on that list, not a free 0–100 number.noul:instructionsis a statement. The resultnoulis the probability it is true, from 0 to 1.
Read probabilities and confidence before acting. A split near 0.5 is not a decision. If the tool returns System One error, say so. Do not invent probabilities.
After the result
You still write the user-facing answer. The decision result picks or gates. It does not replace the reply.
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.
- 10d ago First seen · 38 lines · 36 tokens per session scan A b7b0fa4fc666
typed-decision is a skill published in the GitHub repository javded-itres/Holix (17 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 381 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-07.
Other skills, from other repositories
mnemosyne
Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.
mnemosyne-memory-override
Hard rule override that forces Mnemosyne for all durable memory storage. The legacy memory tool is DEPRECATED for user preferences, credentials, and project conventions. Use memory ONLY for ephemeral session state.
hermes-tweet
Use Xquik in Hermes Agent for public X research, monitoring, thread summaries, creator discovery & approved actions. Not affiliated with X Corp. Use when the user requests X data or a named action. Trigger with "search X", "monitor X", "post tweet", or "X trends".
vrc-monitor-agent
Use for VRChat friend queries (online status, who played with whom, activity timelines, online patterns) and VRChat social actions (boop, invite, join world, friend management, group operations, image uploads) via the vrc-monitor MCP server on port 8799.
review-workflow
A review workflow for GitHub pull requests and issues, including judging whether changes can be merged or an issue can be closed. It requires read-only review, REST API access, and testing changes in practice.
vrchat-social-queries
VRChat social queries: online, companions, patterns, boops.