How do I install the Gauge skill?

Run npx skillmds@latest add modbender/gauge in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Gauge skill do?

Gauge Memory 📊 It is listed under AI & ML on SkillMD.

Is Gauge safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Gauge?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Gauge free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

modbender (@modbender) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Gauge by modbender — Agent Skill

Name: Gauge
Author: modbender

File contents

Gauge Memory 📊

Status: 📋 Agent Guideline | Module: gauge | Part of: Agent Brain

Confidence classification and self-awareness. Honest about what is known vs. unknown.

What It Does

Guides how the agent interprets and communicates confidence in memory-based claims. Does NOT assign numeric scores.

Confidence Categories

Level	Meaning	When to Use	Language
SURE	Directly stated by user, or 3+ successful applications	User said "Remember: X", or `success` called 3+ times	State it as fact
LIKELY	Non-user source, or inferred with some evidence	Ingested content, single indirect mention	"You mentioned..."
UNCERTAIN	Inferred from context, not directly stated	Pattern detected, not confirmed	"I think..." / "It seems like..."
UNKNOWN	No relevant memory exists	Nothing in archive	"I don't have info on that"

How Confidence is Assigned

Confidence is set at creation time based on the source:

source: "user"      → sure    (directly stated by user)
source: "inferred"  → likely  (detected by agent, not confirmed)
source: "ingested"  → likely  (from external content)

Confidence changes over time via:

success command: At 3+ successes, auto-upgrades to sure
update command: Manual upgrade/downgrade
correct command: Supersedes old entry, creates correction with sure
Decay: sure → likely → uncertain when entries go unused (30 * (1 + access_count) days)

Confidence Changes

User Confirms

When a user confirms something you retrieved:

./scripts/memory.sh update <id> confidence sure

User Corrects You

When a user says you got something wrong:

./scripts/memory.sh correct <wrong_id> "Correct information" "Why the old entry was wrong"

This supersedes the wrong entry and creates a correction record for learning.

Successful Application

When a memory was used and the outcome was positive:

./scripts/memory.sh success <id>

At 3+ successes, confidence auto-upgrades to SURE.

When to Apply Gauge

Gauge is a guideline for retrieval, not a standalone step:

Archive retrieves entries matching the query
Each entry already has a confidence field
The agent reads that field and adjusts language accordingly

Self-Monitoring

Before Responding

Do retrieved memories actually answer the question?
Are there conflicting entries? (→ run conflicts)
Is confidence level appropriate for the stakes?

After Responding

Did the user correct you? → Use correct to track the mistake
Did the user confirm? → Use update to upgrade confidence

What Gauge Does NOT Do

Assign 0.0-1.0 numeric confidence scores (fake precision)
Automatically determine confidence from access count at creation time
Run as code — it's a guideline for how the agent interprets the confidence field

---name: gaugedescription: Gauge Memory 📊---# Gauge Memory 📊**Status:** 📋 Agent Guideline | **Module:** gauge | **Part of:** Agent BrainConfidence classification and self-awareness. Honest about what is known vs. unknown.## What It DoesGuides how the agent interprets and communicates confidence in memory-based claims. Does NOT assign numeric scores.## Confidence Categories| Level | Meaning | When to Use | Language ||-------|---------|-------------|----------|| **SURE** | Directly stated by user, or 3+ successful applications | User said "Remember: X", or `success` called 3+ times | State it as fact || **LIKELY** | Non-user source, or inferred with some evidence | Ingested content, single indirect mention | "You mentioned..." || **UNCERTAIN** | Inferred from context, not directly stated | Pattern detected, not confirmed | "I think..." / "It seems like..." || **UNKNOWN** | No relevant memory exists | Nothing in archive | "I don't have info on that" |## How Confidence is AssignedConfidence is set at creation time based on the source:```source: "user" → sure (directly stated by user)source: "inferred" → likely (detected by agent, not confirmed)source: "ingested" → likely (from external content)```Confidence changes over time via:- `success` command: At 3+ successes, auto-upgrades to `sure`- `update` command: Manual upgrade/downgrade- `correct` command: Supersedes old entry, creates correction with `sure`- Decay: `sure` → `likely` → `uncertain` when entries go unused (30 * (1 + access_count) days)## Confidence Changes### User ConfirmsWhen a user confirms something you retrieved:```bash./scripts/memory.sh update <id> confidence sure```### User Corrects YouWhen a user says you got something wrong:```bash./scripts/memory.sh correct <wrong_id> "Correct information" "Why the old entry was wrong"```This supersedes the wrong entry and creates a correction record for learning.### Successful ApplicationWhen a memory was used and the outcome was positive:```bash./scripts/memory.sh success <id>```At 3+ successes, confidence auto-upgrades to SURE.## When to Apply GaugeGauge is a guideline for retrieval, not a standalone step:1. Archive retrieves entries matching the query2. Each entry already has a `confidence` field3. The agent reads that field and adjusts language accordingly## Self-Monitoring### Before Responding- Do retrieved memories actually answer the question?- Are there conflicting entries? (→ run `conflicts`)- Is confidence level appropriate for the stakes?### After Responding- Did the user correct you? → Use `correct` to track the mistake- Did the user confirm? → Use `update` to upgrade confidence## What Gauge Does NOT Do- Assign 0.0-1.0 numeric confidence scores (fake precision)- Automatically determine confidence from access count at creation time- Run as code — it's a guideline for how the agent interprets the `confidence` field

Frequently asked questions

Gauge