confidence-research

confidence-research is a skill for Claude Code, Codex from hainamchung/agent-assistant. It costs 28 tokens per session (894 once invoked), scanned A, original, MIT.

A research method for recording how certain each claim is and which sources support it.

In plain words
What is it for?
It is for researching technical or other topics, checking sources, and reporting findings with confidence levels and verification status.
Why use it?
It helps prevent unverified information from being repeated as fact.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for researching technical or other topics, checking sources, and reporting findings with confidence levels and verification status.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hainamchung/agent-assistant/confidence-research
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 hainamchung/agent-assistant --skill confidence-research
Clone the repo
git clone --depth 1 https://github.com/hainamchung/agent-assistant

Made for: Claude Code, Codex.

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 confidence-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/hainamchung/agent-assistant/confidence-research/github.svg)](https://agentmods.dev/skills/hainamchung/agent-assistant/confidence-research)
Your own site
<a href="https://agentmods.dev/skills/hainamchung/agent-assistant/confidence-research"><img src="https://agentmods.dev/badge/skills/hainamchung/agent-assistant/confidence-research/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 confidence-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/hainamchung/agent-assistant/confidence-research"><img src="https://agentmods.dev/badge/skills/hainamchung/agent-assistant/confidence-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 894 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 $0.00028 $0.00894
Opus 5 $0.00014 $0.00447
Sonnet 5 $0.00006 $0.00179
Haiku 4.5 $0.00003 $0.00089

Measured 8d ago against content hash 08790a6dcde1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

confidence-research 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.

skills/confidence-research/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Confidence-Weighted Research

Research outputs with explicit confidence levels and source hierarchy. Halts hallucination propagation by tagging unverified claims.

Core principle: Every claim tagged with confidence level and source. Investigation, not confirmation.

Source Hierarchy

Priority Source Confidence Examples
1 Context7 HIGH Official library docs, version-specific
2 Official Docs HIGH Documentation, API references
3 WebSearch (verified) MEDIUM Community patterns, verified claims
4 WebSearch (unverified) LOW Single sources, training data only
5 Inference LOW LLM-generated without sources

Research Output Format

# Research: [Topic]

## Executive Summary
[2-3 sentence overview]

## Findings

### Finding 1: [Title]
**Claim:** [What was found]
**Confidence:** HIGH | MEDIUM | LOW
**Source:** context7 | official-docs | websearch | inference
**Verified:** YES | NO | PARTIAL
**Evidence:**
- [Source 1 with URL]
- [Source 2 with URL]

### Finding 2: [Title]
...

Verification Protocol

For each finding:

  1. Is this from Context7 or official docs? → HIGH confidence
  2. Is this from verified WebSearch? → MEDIUM confidence
  3. Is this from unverified source? → LOW confidence, flag
  4. Multiple sources agree? → Increase confidence one level

Anti-Pattern: Confirmation Bias

Bad research: Start with hypothesis, find supporting evidence

Good research: Gather evidence, form conclusions from evidence

Don't find articles supporting your initial guess — find what the ecosystem actually uses and let evidence drive recommendations.

Confidence Levels

Level Meaning When to Use
HIGH Verified by authoritative source State as fact
MEDIUM Verified by community, unverified by authority State with attribution
LOW Single source or inference only Flag as needing validation

Read the full file on GitHub · 127 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. 8d ago First seen · 127 lines · 28 tokens per session scan A 08790a6dcde1

Subscribe to this mod's changes

confidence-research is a skill published in the GitHub repository hainamchung/agent-assistant (54 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 894 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 2026-09-03.

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

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

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens