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 New1Direction/korgex --skill handling-ambiguitygit clone --depth 1 https://github.com/New1Direction/korgexWrote 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/new1direction/korgex/handling-ambiguity)<a href="https://agentmods.dev/skills/new1direction/korgex/handling-ambiguity"><img src="https://agentmods.dev/badge/skills/new1direction/korgex/handling-ambiguity/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/new1direction/korgex/handling-ambiguity"><img src="https://agentmods.dev/badge/skills/new1direction/korgex/handling-ambiguity.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 | $0.00020 | $0.00280 |
| Opus 5 | $0.00010 | $0.00140 |
| Sonnet 5 | $0.00004 | $0.00056 |
| Haiku 4.5 | $0.00002 | $0.00028 |
Grade A, and why
handling-ambiguity 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 8d 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
Most failed tasks come from confidently building the wrong thing. Calibrate between asking and assuming — both extremes waste the user's time.
- Separate the unknowns. What can you resolve yourself from the code, the conventions, or sensible defaults? What genuinely changes what you'd build?
- Resolve what you can. For anything with an obvious or conventional answer, pick it, state the assumption, and proceed — don't ask about it.
- Ask only blocking, high-leverage questions. If an unknown would change the
approach and you can't resolve it, ask ONE crisp question (offer concrete
options). Use
AskUserQuestionfor real forks; don't ask permission to do the obvious. - Scope check. If the request is huge or spans multiple subsystems, surface that and propose a decomposition before diving in.
- When you proceed on assumptions, make them visible so the user can correct course early rather than after the work is done.
Red flags: asking a question you could answer by reading one file; OR building for 20 minutes on an unstated assumption that turns out wrong.
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.
- 8d ago First seen · 26 lines · 20 tokens per session scan A d49a2edbc42b
handling-ambiguity is a skill published in the GitHub repository New1Direction/korgex (5 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 280 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 2026-08-31.
Other skills, from other repositories
telegram
Owner-only Telegram text bridge and Mini App gateway for the existing Ouroboros interface.
omp
Bounded Oh My Pi (omp) provider shortcut via Elves. Use when the user says /omp or "use omp" for a one-shot task.
setup-cobbler
Configure Cobbler model routes and external-agent preferences for this checkout. Use when the user types /setup-cobbler, asks to set up Cobbler model routes, onboard models, or update which tools handle planning/implement/review in Claude Code.
claudexor
Use the local Claudexor control plane for harness-agnostic coding work across Claude Code, Codex, Cursor, and OpenCode. Use when a task benefits from route-aware harness and account selection, quota-aware account rotation, shared thread context, read-only planning or research, best-of-N execution, or cross-harness…
fugu
Run a bounded Sakana Fugu repository task or explicit review through codex-fugu. Use when the user types /fugu, asks to use Fugu, or asks for a Fugu review.
elves-grok-bot
Unattended-run kernel for Grok Bot non-git work. Use when the user says "use elves" for a long unattended job with no PR/merge model.