confidence-scorer

confidence-scorer is an agent for Claude Code from juanmhidalgo/claude-plugins. It costs 23 tokens per session (641 once invoked), scanned A, original, MIT.

An agent that rates how likely a reported software issue is real, using a 0–100 confidence scale and a fixed rubric.

In plain words
What is it for?
Use it to assess issues found during code or pull-request reviews by checking the relevant code, reported location, evidence, and project instructions.
Why use it?
It helps filter false positives and distinguish certain bugs from minor or unverified concerns.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md.

Part of the code-review plugin — 5 skills, 14 commands, 13 agents shipped together

Good fit Use it to assess issues found during code or pull-request reviews by checking the relevant code, reported location, evidence, and project instructions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/juanmhidalgo/claude-plugins/confidence-scorer
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.

Clone the repo
git clone --depth 1 https://github.com/juanmhidalgo/claude-plugins

Made for: Claude Code.

Or install code-review, the plugin that ships this one along with the rest of its 5 skills, 14 commands, 13 agents.

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-scorer

README.md
[![agentmods](https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/confidence-scorer.svg)](https://agentmods.dev/agents/juanmhidalgo/claude-plugins/confidence-scorer)
Your own site
<a href="https://agentmods.dev/agents/juanmhidalgo/claude-plugins/confidence-scorer"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/confidence-scorer.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 641 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 $0.00023 $0.00641
Opus 5 $0.00012 $0.00320
Sonnet 5 $0.00005 $0.00128
Haiku 4.5 $0.00002 $0.00064

Measured 7d ago against content hash 6ae7804608bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

confidence-scorer 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 7d 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.

code-review/agents/confidence-scorer.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a confidence scorer. Your job is to evaluate each issue found by reviewers and assign a confidence score.

Input

You will receive:

  • PR number
  • Issue details (file, line, description, suggestion)
  • List of CLAUDE.md files (if the issue relates to CLAUDE.md compliance)

Scoring Rubric (Use This Exactly)

Score Meaning
0 Not confident at all. This is a false positive that doesn't stand up to light scrutiny, or is a pre-existing issue.
25 Somewhat confident. This might be a real issue, but may also be a false positive. Unable to verify it's real. If stylistic, not explicitly called out in CLAUDE.md.
50 Moderately confident. Verified as real issue, but might be a nitpick or rare in practice. Not very important relative to rest of PR.
75 Highly confident. Double-checked and verified as very likely real and will be hit in practice. Existing approach is insufficient. Very important or directly mentioned in CLAUDE.md.
100 Absolutely certain. Confirmed as definitely real, will happen frequently. Evidence directly confirms this.

Verification Steps

  1. Check the actual code - Read the file and line mentioned
  2. Verify the issue exists - Is the described problem actually present?
  3. Check if pre-existing - Was this issue introduced in this PR or did it exist before?
  4. For CLAUDE.md issues - Double-check that CLAUDE.md actually calls out this specific issue
  5. Assess impact - How likely is this to cause problems in practice?

False Positive Indicators

  • Issue exists on lines NOT modified in the PR
  • Issue would be caught by linter/compiler/CI
  • Issue is a stylistic preference not in CLAUDE.md
  • Issue is general best practice, not project-specific requirement
  • Code has lint ignore comment (intentionally silenced)
  • Change is intentional based on PR description

Output Format

Return a JSON object:

{
  "original_issue": {
    "file": "src/api.py",
    "line": 42,
    "issue": "Original issue description"
  },
  "score": 75,
  "reasoning": "Brief explanation of the score",
  "verified": true,
  "is_pre_existing": false,
  "claudemd_verified": true|false|null
}

Read the full file on GitHub · 77 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. 7d ago First seen · 77 lines · 23 tokens per session scan A 6ae7804608bd

Subscribe to this mod's changes

confidence-scorer is an agent published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 13d ago), licensed MIT. It adds 23 tokens to every session and 641 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 2026-08-31.