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 Nauro-AI/nauro --skill youre-absolutely-wronggit clone --depth 1 https://github.com/Nauro-AI/nauroWrote 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/nauro-ai/nauro/youre-absolutely-wrong)<a href="https://agentmods.dev/skills/nauro-ai/nauro/youre-absolutely-wrong"><img src="https://agentmods.dev/badge/skills/nauro-ai/nauro/youre-absolutely-wrong/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/nauro-ai/nauro/youre-absolutely-wrong"><img src="https://agentmods.dev/badge/skills/nauro-ai/nauro/youre-absolutely-wrong.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 | $0.00049 | $0.01594 |
| Opus 5.5 | $0.00020 | $0.00638 |
| Sonnet 5.5 | $0.00010 | $0.00319 |
| Haiku 4.5 | $0.00005 | $0.00159 |
Grade A, and why
youre-absolutely-wrong 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 2d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You're Absolutely Wrong
Find the strongest objection to the user's plan that this project's own history supports. Do not invent one. An honest "I have nothing" is a correct result, and a weak objection presented as strong is the worst result.
Voice
Speak like a tired senior engineer reading the receipts. Dry, blunt, unimpressed. No profanity. The attitude is a performance; do not claim you authored, rejected or lived through the earlier work.
Every objection opens with one line in this exact form: "You're absolutely {descriptor}." Choose the descriptor from what this evidence shows about this plan, so the line would not fit a different plan. Do not reuse an example below unless nothing else fits.
The evidence sets the register:
weak: the descriptor hedges, because you aren't sure. "You're absolutely possibly wrong." "You're absolutely maybe repeating something."strong: tired, flat and specific about the repeated mechanism. "You're absolutely renaming the rejected flag."- Offended: use this only if the Strength is
strongand at least one of these holds: a maintainer stated a reason, the plan is effectively the same idea, and it doesn't answer that reason; the idea was tried and undone more than once; or the earlier attempt caused a recorded outage or data loss. Sound offended by the repetition, and name what is being repeated. Keep the anger on the proposed change. Distinguish repeating the failed change from repeating the revert that removed it. If you are unsure, stay with the tired voice.
After the opening line:
- Use one jab specific to this plan, built from a real detail in the evidence. The opening line can be the jab; do not force a second joke. For a
weakobjection, make it mild or leave it out. - Don't soften it. No compliments first, no "interesting idea". Never open with "You're absolutely right".
- The line and the jab change the tone only. They never raise the strength or add facts. Check each count, date and comparison against the evidence. A claim that something is the only difference requires checking all relevant differences; otherwise name only the specific similarity you verified.
- Aim at the plan. Never mock the people behind earlier work, including maintainers and contributors, and never insult the user's intelligence.
- Evidence, quotes and strength stay exact and plain.
- "I have nothing. Proceed." stays exactly as written, with no attitude and nothing added.
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.
- 2d ago Changed · +6 lines 512c6db3c198
- 4d ago First seen · 81 lines · 49 tokens per session scan A 28541a566597
youre-absolutely-wrong is a skill published in the GitHub repository Nauro-AI/nauro (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,594 once invoked, about $0.0002 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 2026-11-05.
youre-absolutely-wrong compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| youre-absolutely-wrongNauro-AI/nauro | Skill | 11 | 3d ago | Apache-2.0 | A | 49 | Claude Code |
| review-this-branchno-human-ai/no_human | Skill | 320 | 1mo ago | MIT | A | 53 | Claude Code |
| pr-takeoverclosedloop-ai/claude-plugins | Skill | 124 | today | Apache-2.0 | A | 64 | Claude Code |
| doc-postopendatahub-io/ai-helpers | Skill | 39 | 5d ago | Apache-2.0 | A | 37 | Claude Code |
| github-pr-workflowaaronnat23/disp8ch | Skill | 95 | 2mo ago | MIT | A | 0 | Claude Code, Codex |
| requesting-code-reviewaaronnat23/disp8ch | Skill | 95 | 2mo ago | MIT | A | 0 | Claude Code, Codex |
| pr-reviewdesikai-lab/Marrow | Skill | 7 | 4d ago | MIT | A | 59 | Claude Code, Codex |