trust-calibration

trust-calibration is a skill for Claude Code from Owl-Listener/ai-design-skills. It costs 27 tokens per session (1,638 once invoked), scanned A, original, MIT.

A method for helping users trust AI by the right amount for each situation. It considers how confident the AI sounds, its past record, the risks involved, and whether sources or alternatives are visible.

In plain words
What is it for?
Designing confidence signals, showing sources and uncertainty, making risks clear, and identifying patterns that cause overtrust or undertrust.
Why use it?
It helps prevent users from accepting wrong answers too readily or ignoring useful ones because the AI seems unreliable.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-alignment-reasoning plugin — 8 skills, 3 commands shipped together

Good fit Designing confidence signals, showing sources and uncertainty, making risks clear, and identifying patterns that cause overtrust or undertrust.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/owl-listener/ai-design-skills/trust-calibration
Install

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.

Any agent
npx skills add Owl-Listener/ai-design-skills --skill trust-calibration
Clone the repo
git clone --depth 1 https://github.com/Owl-Listener/ai-design-skills

Made for: Claude Code.

Or install ai-alignment-reasoning, the plugin that ships this one along with the rest of its 8 skills, 3 commands.

Wrote 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.

agentmods badge for trust-calibration

README.md
[![agentmods](https://agentmods.dev/badge/skills/owl-listener/ai-design-skills/trust-calibration/github.svg)](https://agentmods.dev/skills/owl-listener/ai-design-skills/trust-calibration)
Your own site
<a href="https://agentmods.dev/skills/owl-listener/ai-design-skills/trust-calibration"><img src="https://agentmods.dev/badge/skills/owl-listener/ai-design-skills/trust-calibration/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.

agentmods 80×15 button for trust-calibration

Your own site · 80×15
<a href="https://agentmods.dev/skills/owl-listener/ai-design-skills/trust-calibration"><img src="https://agentmods.dev/badge/skills/owl-listener/ai-design-skills/trust-calibration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,638 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.01638
Opus 5 $0.00014 $0.00819
Sonnet 5 $0.00005 $0.00328
Haiku 4.5 $0.00003 $0.00164

Measured 13d ago against content hash 6f82115af1af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

trust-calibration 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 13d 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.

claude-plugin/ai-alignment-reasoning/skills/trust-calibration/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trust Calibration

Calibrated trust is the difference between an AI that augments user judgment and one that displaces it. Overtrust causes harm when the AI is wrong. Undertrust wastes the AI when it's right. Both failure modes are common, and neither shows up in standard accuracy metrics.

Designing for trust means giving users the information they need to update their trust appropriately, turn by turn.

What shapes user trust in the moment

  • Surface confidence — how certain the AI sounds, regardless of whether it should
  • Track record — prior interactions in this and previous sessions
  • Stakes legibility — how clearly the user understands what could go wrong
  • Source visibility — whether the AI shows reasoning, sources, or alternatives
  • Persona fit — a "professional" persona gets more trust than a "friendly" one for the same content

These shape trust whether you design for them or not. Designing for them deliberately is what trust calibration is.

Trust failure modes

  • Sycophancy-driven overtrust: AI tells the user what they want to hear; user trusts the agreement and acts on it
  • Confidence-mismatch overtrust: AI sounds certain about something it shouldn't be (hallucinations, edge cases)
  • Defensive undertrust: AI hedges everything ("might be", "could possibly") even when right; user tunes out the qualifier
  • Authority-collapse undertrust: one wrong answer in a high-stakes context destroys trust for the whole product
  • Trust laundering: low-confidence outputs presented with high-confidence formatting (bold headers, decisive bullets) — visual authority disconnected from epistemic authority

Calibration signals from the AI side

The AI shapes trust deliberately through:

  • Confidence markers proportionate to actual epistemic state: "I'm fairly sure" / "I'd verify this" / "I don't know" — used because they're true, not as decoration
  • Source attribution: "According to [X]" rather than unsourced assertion. Cite when possible; flag the gap when not.
  • Alternative surfacing: "Two interpretations: A and B. I went with A because…" — shows the model's working
  • Failure transparency: "I got that wrong earlier — here's the correction." Long-term trust gain at short-term cost.
  • Capability fence-posting: "I can help with X but not Y." Defines the boundary so trust isn't tested in the wrong place.

Read the full file on GitHub · 103 lines

Changes

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.

  1. 13d ago First seen · 103 lines · 27 tokens per session scan A 6f82115af1af

Subscribe to this mod's changes

trust-calibration is a skill published in the GitHub repository Owl-Listener/ai-design-skills (173 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 1,638 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens