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 deciqAI/knowledge-skills --skill confirmation-biasgit clone --depth 1 https://github.com/deciqAI/knowledge-skillsWrote 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/deciqai/knowledge-skills/confirmation-bias)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/confirmation-bias"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/confirmation-bias/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/deciqai/knowledge-skills/confirmation-bias"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/confirmation-bias.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 | $0.00095 | $0.01649 |
| Opus 5 | $0.00048 | $0.00825 |
| Sonnet 5 | $0.00019 | $0.00330 |
| Haiku 4.5 | $0.00010 | $0.00165 |
Grade A, and why
confirmation-bias 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 9d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Confirmation Bias
Overview
Confirmation bias is the systematic tendency to seek, interpret, remember, and weight evidence in ways that support existing beliefs — and to correspondingly miss disconfirming evidence. It is the most-replicated finding in cognitive psychology, documented across cultures, expertise levels, and IQ ranges.
The canonical proof: Wason's 1960 "2-4-6 task" showed ~80% of subjects (including PhD scientists) confidently announced a wrong rule after testing only sequences they expected to confirm — never proposing a sequence designed to refute the hypothesis.
Composes with critical-thinking, bayesian-reasoning, abductive-reasoning, and metacognition.
When to Use
- A team is converging on a single answer too quickly
- You feel confident about a claim and haven't looked for evidence against it
- Research or due diligence keeps "validating" existing beliefs
- Someone says "cherry-picking," "echo chamber," or "looking for what you want to see"
- A team is committing to an AI thesis (AI capex, AI valuations, or AI adoption) by citing confirming demos and adoption while discounting failed eval results
Not when: explicit advocacy context; very low-stakes decision; cost of disconfirmation exceeds value of decision.
Coaching Novices (Adaptive Front Door)
- Engine mode: user has a concrete case → run The Process directly.
- Coach mode: user is unfamiliar or has no concrete case → guide step by step.
In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.
- One-liner: before trusting evidence that supports your view, ask what would have changed your mind — and whether you actually looked for it.
- Check fit against When to Use / When NOT to use.
- Elicit the specific claim and evidence cited.
[WAIT — do not advance until user responds]
- One question at a time: what would falsify this? Did you look for that? What's the strongest counter-evidence? How did you treat it?
[WAIT — do not advance until user responds]
- Close: name the falsification test + structural countermeasure (Devil's advocate, red team, blind evaluation).
[WAIT — do not advance until user responds]
What ships with it
4 files 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.
- 9d ago First seen · 112 lines · 95 tokens per session scan A 5f46091d6512
confirmation-bias is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 7d ago), licensed MIT. It adds 95 tokens to every session and 1,649 once invoked, about $0.0005 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
edge-tts
Text-to-speech conversion using uvx edge-tts for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS…
mcp-deepwiki
Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.
tianqi
A weather-lookup workflow for Chinese locations, covering forecasts, hourly conditions, weather warnings, and daily-life indexes.
cto-advisor
Records technical decisions that serve a business outcome: constraints, architecture options, build-or-buy tradeoffs, and a justified skill selection. Use when the CEO asks "which architecture fits", "should we build or buy", "which skill should this department use", or "review our technical plan".
compliance-check
Compliance pre-flight for a feature, campaign, or initiative — maps the data and activity involved, checks applicable regimes (privacy/GDPR-style, consumer protection, marketing rules, sector-specific), lists required approvals and notices, builds a gap list with remediation owners, and ends in a go/no-go…
journal-entry
Drafts correct double-entry journal entries from described business events, with templates for accruals, deferrals, depreciation, payroll, prepaids, and corrections. Every entry carries a date, memo, and support reference; reversals are drafted where due; a running debits-equal-credits check covers each entry and the…