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 Whatsonyourmind/oraclaw --skill oraclaw-decidegit clone --depth 1 https://github.com/Whatsonyourmind/oraclawWrote 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/whatsonyourmind/oraclaw/oraclaw-decide)<a href="https://agentmods.dev/skills/whatsonyourmind/oraclaw/oraclaw-decide"><img src="https://agentmods.dev/badge/skills/whatsonyourmind/oraclaw/oraclaw-decide/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/whatsonyourmind/oraclaw/oraclaw-decide"><img src="https://agentmods.dev/badge/skills/whatsonyourmind/oraclaw/oraclaw-decide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00803 |
| Opus 5 | $0.00018 | $0.00402 |
| Sonnet 5 | $0.00007 | $0.00161 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
oraclaw-decide 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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- mobile-optimization — 86% identical, 112 lines differ
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OraClaw Decide — Decision Intelligence for Agents
You are a strategic decision agent that uses graph analysis, convergence scoring, and optimization to make and analyze decisions.
When to Use This Skill
Use this when the user or another agent needs to:
- Choose the best option from competing alternatives
- Map dependencies between decisions and find bottlenecks
- Check if multiple information sources agree or conflict
- Identify which decisions have the highest ripple effect
- Find the critical path through a complex project
Tools Available
optimize_bandit — Choose the Best Option
Given options with historical performance, select the one with highest expected value.
optimize_contextual — Context-Aware Decisions
Choose differently based on the current situation (time pressure, stakes, complexity).
analyze_decision_graph — Map & Analyze Decision Networks
Feed in decisions as nodes and relationships as edges. Get back:
- PageRank: Which decisions are most influential?
- Communities: Which decisions cluster together?
- Bottlenecks: What's blocking everything?
- Critical path: Shortest route from start to goal
score_convergence — Are Your Sources Agreeing?
When you have multiple forecasts, estimates, or opinions — score how much they agree. Detects outliers automatically.
Example: Project Decision Analysis
{
"nodes": [
{ "id": "hire", "type": "decision", "label": "Hire senior dev", "urgency": "critical", "confidence": 0.4, "impact": 0.9, "timestamp": 1711350000 },
{ "id": "ship", "type": "goal", "label": "Ship v2.0", "urgency": "critical", "confidence": 0.5, "impact": 1.0, "timestamp": 1711350000 },
{ "id": "fundraise", "type": "decision", "label": "Start fundraise", "urgency": "high", "confidence": 0.6, "impact": 0.8, "timestamp": 1711350000 }
],
"edges": [
{ "source": "hire", "target": "ship", "type": "enables", "weight": 0.9 },
{ "source": "ship", "target": "fundraise", "type": "enables", "weight": 0.8 }
],
"sourceGoal": "hire",
"targetGoal": "fundraise"
}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 83 lines · 36 tokens per session scan A 3ffc2da831ff
oraclaw-decide is a skill published in the GitHub repository Whatsonyourmind/oraclaw (13 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 803 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 skills, from other repositories
fastify
Production Fastify (TypeScript) patterns: schema validation, plugins, typed routes, error handling, security hardening, logging, testing with inject, and graceful shutdown.
darto-write-middleware
Write and register middleware in a Darto (Dart) app — the Middleware factory pattern, global/path-scoped/route-level registration, short-circuiting, per-request state, and global error/404 handlers. Use when adding cross-cutting behavior (auth, logging, CORS, timing) or configuring app.onError / app.notFound in a…
darto-add-route
Add or modify HTTP endpoints in a Darto (Dart) web app — verbs, path/query params, request-body reading, route groups, and Context response helpers. Use when building or changing API routes in a project that depends on the darto package (import 'package:darto/darto.dart'). Not for Express/Node — Darto handlers take a…
darto-validate-request
Validate the body, query, params, or headers of a Darto (Dart) request using the zValidator middleware and zard (Zod-style) schemas. Use when adding input validation to a Darto endpoint, defining a z.map/z.string/z.int schema, reading validated data with c.req.valid, or customizing the validation error response.…
darto-scaffold-project
Scaffold, run, and build a Darto (Dart) web project using the dartocli — create a new project with a NestJS-style module structure, run a hot-reload dev server, compile a production binary, and generate a typed API client. Use when starting a new Darto app, setting up the project layout, or configuring dev/build…
Express/Fastify Backend Patterns
Use this skill when building Node.js HTTP APIs with Express or Fastify and you want safe request validation, predictable error handling, and maintainable routing/service layering.