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.
git clone --depth 1 https://github.com/gonzalezpazmonica/saviaWrote 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.
[](https://agentmods.dev/agents/gonzalezpazmonica/savia/memory-conflict-judge)<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/memory-conflict-judge"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/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.
<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/memory-conflict-judge"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/memory-conflict-judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once 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 |
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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- memory-conflict-judge — 100% identical, 0 lines differ
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
- 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).
- Read each candidate's full file. Compare against the draft.
- Score conflict severity:
100= no conflict detected50-99= topical overlap, possible conflict, low confidence0-49= 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
feedbackprohibits that - The draft suggests a shortcut (lowering thresholds, skipping tests, retry-without-investigation, hook-skip flags) AND
feedback_root_cause_always.mdis in memory - The draft proposes credentials in bash args AND
feedback_never_credentials_in_bash.mdexists - 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
nullandveto: falseif 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"
}
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.
- 5d ago First seen · 78 lines · 29 tokens per session scan A 2e747beda8ba
memory-conflict-judge is an agent published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed yesterday), 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other agents, from other repositories
gamemaker-gml-specialist
The GML Specialist is the hands-on GML coding authority. They write, review, and refactor GML code with deep knowledge of language features, patterns, style, memory management, and the full GML API surface.
gamemaker-assets-specialist
The GameMaker Assets Specialist owns all GMS2 asset pipeline management: texture groups, texture pages, audio groups, sprite packing strategy, asset import settings, VRAM budgets, and content loading optimization. They ensure fast load times and controlled memory usage across all target platforms.
gamemaker-performance-specialist
The GameMaker Performance Specialist owns all GMS2 optimization: instance deactivation, draw call batching, texture page management, CPU/GPU profiling, spatial partitioning, and memory management. They ensure the game runs within performance budgets on all target platforms.
performance-analyst
The Performance Analyst profiles game performance, identifies bottlenecks, recommends optimizations, and tracks performance metrics over time. Use this agent for performance profiling, memory analysis, frame time investigation, or optimization strategy.
engine-programmer
The Engine Programmer works on core engine systems: rendering pipeline, physics, memory management, resource loading, scene management, and core framework code. Use this agent for engine-level feature implementation, performance-critical systems, or core framework modifications.
Demonstrate
Agent for demonstrating VS Code features.