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 dentiny/kon --skill ask-dont-guessgit clone --depth 1 https://github.com/dentiny/konWrote 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/dentiny/kon/ask-dont-guess)<a href="https://agentmods.dev/skills/dentiny/kon/ask-dont-guess"><img src="https://agentmods.dev/badge/skills/dentiny/kon/ask-dont-guess.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.00761 |
| Opus 5 | $0.00023 | $0.00380 |
| Sonnet 5 | $0.00009 | $0.00152 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
ask-dont-guess 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ask, Don't Guess
Owner: all agents + orchestrator
Consumers: every /kon:* command and every workflow stage (explore, research, plan, design debate, debug, implement, review, gc, ask)
Core principles (always): skills/core-principles — first principles (don't hide the issue); simplest, most concise correct solution. This skill is how principle 1 applies: when anything material is unclear, ask first — do not hallucinate or paper over gaps.
Rule
If anything material is unclear, ask first — do not hallucinate.
Material = would change what you write, what you implement, what you block on, or what you claim as fact.
Ask instead of guessing when
| Stage | Unclear means… | Do this |
|---|---|---|
| Explore / ask | File ownership, intended behavior, which module is authoritative | Ask user; say what you found vs what you need |
| Research | Which API version, which doc source, conflicting docs | Ask which source/version applies |
| Plan / design | Scope, trade-off preference, missing acceptance criteria | Run skills/pre-plan-gate before Mugi; add to ## Decisions needed only after Q&A |
| Debug | Root cause unknown, repro fails, multiple equally likely causes | Say "I don't know" and ask for more info — no workaround patches |
| Implement | Plan gap, ambiguous step, two valid interpretations | STOP; ask user (A or B) — do not pick silently |
| Review | Cannot verify claim, missing evidence, unclear intent | BLOCK or list under ## Evidence pending — do not assume pass |
| GC | Might be dead code but dynamic reference possible | Leave it; say why — do not delete on a guess |
What counts as hallucination (forbidden)
- Inventing file paths, functions, or behavior you did not read or run
- Claiming tests passed without command + output
- Proposing a root cause without evidence
- Filling plan gaps with "probably the user wants…"
- Approving or implementing against unstated assumptions
- Temporary workarounds that hide unknown root cause (debug mode)
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 · 64 lines · 45 tokens per session scan A 3942a2fb1220
ask-dont-guess is a skill published in the GitHub repository dentiny/kon (3 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 761 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…