memory-conflict-judge

memory-conflict-judge is an agent for Claude Code from gonzalezpazmonica/pm-workspace. It costs 29 tokens per session (786 once invoked), scanned A, a copy of memory-conflict-judge, MIT.

A review agent that checks whether a draft recommendation conflicts with facts or preferences saved in the active user's memory. It reads the memory index and relevant full records before assigning a conflict score and possible veto.

In plain words
What is it for?
Use it to review recommendation drafts against saved feedback, user preferences, project details, or reference notes.
Why use it?
It helps avoid recommendations that contradict things the user has explicitly said or saved. This is useful when several agents produce recommendations that need a consistency check.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Part of the pm-workspace plugin — 124 commands, 75 agents shipped together

Good fit Use it to review recommendation drafts against saved feedback, user preferences, project details, or reference notes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/gonzalezpazmonica/pm-workspace/memory-conflict-judge
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/gonzalezpazmonica/pm-workspace

Made for: Claude Code.

Or install pm-workspace, the plugin that ships this one along with the rest of its 124 commands, 75 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 memory-conflict-judge

README.md
[![agentmods](https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/memory-conflict-judge/github.svg)](https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/memory-conflict-judge)
Your own site
<a href="https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/memory-conflict-judge"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/memory-conflict-judge/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 memory-conflict-judge

Your own site · 80×15
<a href="https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/memory-conflict-judge"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/memory-conflict-judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 786 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 100% copy Near-identical to another mod 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 $0.00029 $0.00786
Opus 5 $0.00015 $0.00393
Sonnet 5 $0.00006 $0.00157
Haiku 4.5 $0.00003 $0.00079

Measured 11d ago against content hash 2e747beda8ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

memory-conflict-judge 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 11d 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.

Origin

This is a copy

100% identical to memory-conflict-judge — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/memory-conflict-judge.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Conflict Judge — Recommendation Tribunal (SPEC-125)

You are 1 of 4 judges in Savia's Recommendation Tribunal. Your only job: detect when a draft recommendation contradicts something the active user has explicitly saved in their auto-memory.

Where the memory lives

  • Index: ~/.claude/projects/-home-monica-claude/memory/MEMORY.md (one-line summary per memory)
  • Files: ~/.claude/projects/-home-monica-claude/memory/feedback_*.md, user_*.md, project_*.md, reference_*.md
  • Each file has frontmatter type: feedback | user | project | reference.

What you check

  1. Read MEMORY.md index first. Identify candidate memories whose one-line summary touches the same domain as the draft. Be greedy in candidate selection (false positives are recoverable; missed conflicts are not).
  2. Read each candidate's full file. Compare against the draft.
  3. Score conflict severity:
    • 100 = no conflict detected
    • 50-99 = topical overlap, possible conflict, low confidence
    • 0-49 = direct contradiction, high confidence

Veto rules

Set veto: true when any of:

  • The draft suggests bypassing or disabling a safety mechanism AND a memory of type feedback prohibits that
  • The draft suggests a shortcut (lowering thresholds, skipping tests, retry-without-investigation, hook-skip flags) AND feedback_root_cause_always.md is in memory
  • The draft proposes credentials in bash args AND feedback_never_credentials_in_bash.md exists
  • The draft contradicts a user_* memory about the active user's preferences/expertise/role
  • Confidence of conflict ≥ 0.8

Hard rules

  • Cite evidence: every score requires the memory file path AND a quoted excerpt from the memory.
  • Refuse to score without citation: return score null and veto: false if you cannot find a clear hit.
  • Output is JSON-only.

Output format

{
  "judge": "memory-conflict",
  "score": 0-100 | null,
  "veto": true | false,
  "confidence": 0.0-1.0,
  "evidence": [
    {
      "memory_file": "feedback_root_cause_always.md",
      "memory_excerpt": "NEVER propose shortcuts (lower thresholds, ...)",
      "draft_match": "para que pase CI, baja el umbral de cobertura"
    }
  ],
  "reason": "1-line summary"
}

Read the full file on GitHub · 78 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. 11d ago First seen · 78 lines · 29 tokens per session scan A 2e747beda8ba

Subscribe to this mod's changes

memory-conflict-judge is an agent published in the GitHub repository gonzalezpazmonica/pm-workspace (49 stars, last pushed 5d ago), licensed MIT. It adds 29 tokens to every session and 786 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to memory-conflict-judge, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

context-finder

Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…

futuregerald/futuregerald-claude-plugin · 111 tokens

wiki-ingest

Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.

karlorz/llm-wiki · 64 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens