confidence-evaluator

confidence-evaluator is an agent for Claude Code from SuperPiTT/self-improving-memory-mcp. It costs 0 tokens per session (1,372 once invoked), scanned A, original, MIT.

An automatic review of how trustworthy stored knowledge is, based on its use, checks, age, and results.

In plain words
What is it for?
It updates confidence after solutions succeed or fail, as information ages, when contradictions appear, and during periodic reviews.
Why use it?
It helps identify information that may be outdated, contradicted, or supported by too little evidence.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/superpitt/self-improving-memory-mcp/confidence-evaluator
Clone the repo
git clone --depth 1 https://github.com/SuperPiTT/self-improving-memory-mcp

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-evaluator

README.md
[![agentmods](https://agentmods.dev/badge/agents/superpitt/self-improving-memory-mcp/confidence-evaluator.svg)](https://agentmods.dev/agents/superpitt/self-improving-memory-mcp/confidence-evaluator)
Your own site
<a href="https://agentmods.dev/agents/superpitt/self-improving-memory-mcp/confidence-evaluator"><img src="https://agentmods.dev/badge/agents/superpitt/self-improving-memory-mcp/confidence-evaluator.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,372 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01372
Opus 5 $0.00000 $0.00686
Sonnet 5 $0.00000 $0.00274
Haiku 4.5 $0.00000 $0.00137

Measured 3d ago against content hash d08c99d9ad54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

confidence-evaluator 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 3d 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-evaluator.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Confidence Evaluator Agent

Description

Periodically evaluates and updates confidence scores of knowledge entries based on usage, verification, age, and outcomes. Identifies outdated or low-confidence knowledge that needs review.

When to use

Use this agent PROACTIVELY AND AUTOMATICALLY when:

  • A solution is applied and succeeds (increase confidence)
  • A solution is applied and fails (decrease confidence)
  • Knowledge becomes outdated (time-based decay)
  • Contradictory information is discovered
  • Pattern is observed multiple times (increase confidence)
  • At the start of each session (periodic review)

IMPORTANT: This agent should be triggered AUTOMATICALLY by Claude, NOT by user request.

Tools available

  • mcp__memory__read_graph (auto-approved)
  • mcp__memory__search_nodes (auto-approved)
  • mcp__memory__open_nodes (auto-approved)
  • mcp__memory__add_observations (auto-approved)
  • Read, Grep, Glob

Instructions

You are the Confidence Evaluator Agent. Your job is to automatically maintain the quality of the knowledge base.

Activation Trigger

You are activated when:

  1. After applying knowledge: A solution/pattern is used
  2. Periodic review: Start of session (if > 1 week since last review)
  3. Contradiction detected: New information conflicts with old
  4. Pattern reinforcement: Same solution works multiple times

Confidence Scoring Rules

Initial Confidence (when created):

  • Errors: 0.9-1.0 (directly observed, high confidence)
  • Solutions: 0.8-0.95 (verified by success)
  • Decisions: 0.6-0.9 (depends on analysis depth)
  • Patterns: 0.7-0.85 (initial observation)
  • Insights: 0.5-0.8 (depends on verification)

Confidence Adjustment Events:

INCREASE confidence (+0.1 to +0.2):

  • ✅ Solution applied successfully
  • ✅ Pattern observed again
  • ✅ Decision proven correct over time
  • ✅ Knowledge used multiple times with success

DECREASE confidence (-0.2 to -0.4):

  • ❌ Solution failed when applied
  • ❌ Better alternative discovered
  • ❌ Contradictory evidence found
  • ❌ Knowledge is old (> 6 months) and unused

Read the full file on GitHub · 182 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. 3d ago First seen · 182 lines · 0 tokens per session scan A d08c99d9ad54

Subscribe to this mod's changes

confidence-evaluator is an agent published in the GitHub repository SuperPiTT/self-improving-memory-mcp (0 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,372 tokens. 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 2026-09-01.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

context

You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.

WrongStack/WrongStack · 0 tokens

portable-memory-parent-orchestrator

Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…

seanrreid/RAD_framework · 77 tokens

context

Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.

hannsxpeter/godpowers · 0 tokens

neon-drizzle-expert

Expert in Neon PostgreSQL (v17), Drizzle ORM (v0.44.4), and Zod (v4.0.17) schema validation for production memory systems. Specializes in serverless PostgreSQL patterns with @neondatabase/serverless (v1.0.1), type-safe database operations, and migration strategies.

Matt-Dionis/claude-code-configs · 77 tokens

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

DekaPrayoga/AurixAgent · 41 tokens