Skip to content
Agentmart
Submit a tool

instruction-conflicts

Audit the layered instruction stack (in-conversation user → soul.md/global → project guide → skill → tool/system) for conflicting or ambiguous directives, and…

Skill by jpvarbed

IndexedLicense unknown★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/jpvarbed-instruction-conflicts

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Audit the layered instruction stack (in-conversation user → soul.md/global → project guide → skill → tool/system) for conflicting or ambiguous directives, and surface which layer should win. Use when the user says "check for instruction conflicts", "do my layers contradict", "audit soul.md vs project/skill", "why is the agent ignoring X", or before relying on a deep skill stack. NOT for scoring one skill's quality (use linting-and-scoring) or auditing whether a skill obeys itself (use the adherence audit). Built from ManyIH (arXiv:2604.09443) via apply-paper.

Use cases: security, research, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/instruction-conflicts

What's inside

Skill name
instruction-conflicts
Description
Audit the layered instruction stack (in-conversation user → soul.md/global → project guide → skill → tool/system) for conflicting or ambiguous directives, and surface which layer should win. Use when the user says "check for instruction conflicts", "do my layers contradict", "audit soul.md vs project/skill", "why is the agent ignoring X", or before relying on a deep skill stack. NOT for scoring one skill's quality (use linting-and-scoring) or auditing whether a skill obeys itself (use the adherence audit). Built from ManyIH (arXiv:2604.09443) via apply-paper.
License
unknown
Instructions
95 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (6)

  • DESIGN.md
  • RECEIPT-2026-07-12.md
  • SKILL.md
  • build_cases.py
  • cases.jsonl
  • config.json

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

Signals

Stars
1
Forks
1
Open issues
0
Last commit (this folder)
Jul 13, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
License unknown
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from jpvarbed

Cite this page

instruction-conflicts skill. Agent Mart. https://agentmart.dev/skills/jpvarbed-instruction-conflicts (last updated 2026-10-24)