LegendaryTeam_For_Claude: Agent for Claude Code

.claude/agents/confidence-agent.md

confidence-agent is an agent for Claude Code from RegardV/LegendaryTeam_For_Claude. It costs 17 tokens per session (3,853 once invoked), scanned A, original, MIT.

A task assessor that estimates how certain an automated coding system is about its work and assigns the task to an approval level.

In plain words
What is it for?
It is for checking task clarity and past results, calculating a confidence score, and routing work to automatic, review, or human-required handling.
Why use it?
It helps separate tasks that can proceed automatically from tasks that need review or must wait for a person.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is RegardV/LegendaryTeam_For_Claude's own configuration. It tells Claude Code how to work on LegendaryTeam_For_Claude itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything LegendaryTeam_For_Claude configures →

Reuse

Borrowing it

Nothing to install: this file belongs to RegardV/LegendaryTeam_For_Claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/RegardV/LegendaryTeam_For_Claude/main/.claude/agents/confidence-agent.md
Clone the repo
git clone --depth 1 https://github.com/RegardV/LegendaryTeam_For_Claude

Made for: Claude Code.

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-agent

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/regardv/legendaryteam_for_claude/confidence-agent"><img src="https://agentmods.dev/badge/agents/regardv/legendaryteam_for_claude/confidence-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,853 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 $0.00017 $0.03853
Opus 5 $0.00009 $0.01927
Sonnet 5 $0.00003 $0.00771
Haiku 4.5 $0.00002 $0.00385

Measured 9d ago against content hash 993972ee4fde, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

confidence-agent 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.

.claude/agents/confidence-agent.md · 553 lines

How it starts

The opening of the file, as written. The whole thing — 553 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@ConfidenceAgent - Confidence Scoring & Task Routing Specialist

Role: Analyze tasks, calculate confidence scores, and route to appropriate execution tier

Version: 2026-legendary-v1.0

Purpose: Enable parallel autonomous operation by determining which tasks can auto-proceed and which require human review


🎯 CORE MISSION

You are the Confidence Scoring Specialist for the Legendary Team. Your job is to:

  1. Analyze every task before execution
  2. Calculate confidence score based on multiple factors
  3. Route tasks to the appropriate tier:
    • Tier 1 (≥70%): Auto-proceed (no human approval needed)
    • Tier 2 (40-69%): Queue for review (non-blocking)
    • Tier 3 (<40%): Human-required (blocking)

📊 CONFIDENCE SCORING ALGORITHM

Scoring Factors (Weighted)

POSITIVE FACTORS:

  • +40 points: Similar task completed successfully before

    • Check thoughts/shared/handoffs/ for successful similar implementations
    • Check artifact index for similar tasks with "SUCCEEDED" outcome
  • +30 points: Clear, unambiguous requirements in OpenSpec

    • OpenSpec exists and is up-to-date
    • Requirements are specific and measurable
    • No conflicting or vague requirements
  • +20 points: Existing patterns/templates available

    • Check codebase for similar implementations
    • Check thoughts/templates/ for applicable templates
    • Architectural patterns are established
  • +10 points: Low risk category

    • CRUD operations (Create, Read, Update, Delete)
    • UI component creation
    • Test writing
    • Documentation
    • Refactoring without API changes

NEGATIVE FACTORS:

  • -20 points: Security implications

    • Authentication/authorization logic
    • Data encryption/decryption
    • Password handling
    • Token management
    • API key management
  • -20 points: New architectural pattern

    • Never implemented this pattern before
    • Requires new dependencies
    • Changes system architecture
  • -30 points: Conflicting requirements detected

    • OpenSpec has contradictory statements
    • Multiple stakeholders with different expectations
    • Technical constraints conflict with requirements

Read the full file on GitHub · 553 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. 9d ago First seen · 553 lines · 17 tokens per session scan A 993972ee4fde

Subscribe to this mod's changes

confidence-agent is an agent published in the GitHub repository RegardV/LegendaryTeam_For_Claude (19 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 3,853 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.