memory-conflicts

memory-conflicts is a command for Claude Code from ArtemioPadilla/agent-triforce. It costs 20 tokens per session (262 once invoked), scanned A, original, MIT.

A command for finding contradictory assessments stored by different coding agents about the same entity.

In plain words
What is it for?
Use it to check, inspect, and resolve cross-agent memory conflicts, such as disagreements about whether a module is stable or fragile.
Why use it?
It helps prevent agents from relying on incompatible shared information. Conflicts can be accepted, investigated, or archived with context for later review.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the agent-triforce plugin — 15 commands, 2 hooks shipped together

Good fit Use it to check, inspect, and resolve cross-agent memory conflicts, such as disagreements about whether a module is stable or fragile.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ArtemioPadilla/agent-triforce
Claude Code
/plugin install agent-triforce

Made for: Claude Code.

Or install agent-triforce, the plugin that ships this one along with the rest of its 15 commands, 2 hooks.

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-conflicts

README.md
[![agentmods](https://agentmods.dev/badge/commands/artemiopadilla/agent-triforce/memory-conflicts/github.svg)](https://agentmods.dev/commands/artemiopadilla/agent-triforce/memory-conflicts)
Your own site
<a href="https://agentmods.dev/commands/artemiopadilla/agent-triforce/memory-conflicts"><img src="https://agentmods.dev/badge/commands/artemiopadilla/agent-triforce/memory-conflicts/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-conflicts

Your own site · 80×15
<a href="https://agentmods.dev/commands/artemiopadilla/agent-triforce/memory-conflicts"><img src="https://agentmods.dev/badge/commands/artemiopadilla/agent-triforce/memory-conflicts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 262 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 $0.00020 $0.00262
Opus 5 $0.00010 $0.00131
Sonnet 5 $0.00004 $0.00052
Haiku 4.5 $0.00002 $0.00026

Measured 9d ago against content hash 36cca1cb914d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

memory-conflicts 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.

agent-triforce/commands/memory-conflicts.md · 20 lines

What it actually says

Check for cross-agent memory conflicts by running the memory sync tool. This detects when two or more agents hold contradictory assessments of the same entity (e.g., one agent considers a module "stable" while another flagged it as "fragile").

Run: python3 ${CLAUDE_PLUGIN_ROOT}/tools/memory-sync.py check

For JSON output: python3 ${CLAUDE_PLUGIN_ROOT}/tools/memory-sync.py check --json

To resolve a conflict:

  • python3 ${CLAUDE_PLUGIN_ROOT}/tools/memory-sync.py resolve <conflict-id> a -- Accept agent A's assessment
  • python3 ${CLAUDE_PLUGIN_ROOT}/tools/memory-sync.py resolve <conflict-id> b -- Accept agent B's assessment
  • python3 ${CLAUDE_PLUGIN_ROOT}/tools/memory-sync.py resolve <conflict-id> investigate -- Mark as under investigation

To view all memory entries: python3 ${CLAUDE_PLUGIN_ROOT}/tools/memory-sync.py show

Resolved conflicts are archived to docs/memory-archive/ with full context for audit trail.

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 · 20 lines · 20 tokens per session scan A 36cca1cb914d

Subscribe to this mod's changes

memory-conflicts is a command published in the GitHub repository ArtemioPadilla/agent-triforce (3 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 262 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 2026-08-31.