# boundary-guardian

boundary-guardian monitors reasoning boundaries and detects semantic drift to stop AI hallucinations before invalid statements occur.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 1357 repo stars
- Author: qdhenry
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/qdhenry/Claude-Command-Suite/tree/HEAD/.claude/agents/wfgy/boundary-guardian.md
- Updated: 2026-03-01
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/boundary-guardian

## What it does

The Sentinel subagent assigns reasoning steps into four color-coded categories based on a tension metric (ΔS): safe, transitional, risk, and danger. Crossing into the danger zone prompts an immediate halt to reasoning and triggers a BBCR sequence to retreat to verified concepts.

It provides built-in commands prefixed with an asterisk, such as `*detect-boundary`, `*assess-risk`, and `*show-heatmap`. Because its command execution resolves against markdown scripts inside `.claude/commands/boundary/` and `.claude/commands/wfgy/`, the agent cannot run those specific procedures if those directories are missing.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/boundary-guardian.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/boundary-guardian.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/boundary-guardian.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/qdhenry/Claude-Command-Suite/tree/HEAD/.claude/agents/wfgy/boundary-guardian.md

## When to use it
- detect when reasoning drifts past verifiable knowledge boundaries
- stop runaway hallucinations using an automated BBCR fallback sequence
- evaluate conversation risk levels across categorized metric zones
- build bridging concepts to explore uncertain topics without guessing

## Example prompts
- Run *detect-boundary to inspect current knowledge limits
- Check the risk score of this explanation with *assess-risk
- Build a safe conceptual path toward the target topic using *find-bridge

## Similar
- [project-boundary](https://affpapa.org/en/nevibecode/plugins/justyna-wojtczak-project-boundary.md) — plugin · ★ 3785 repo stars
- [thinking-circle-of-competence](https://affpapa.org/en/nevibecode/skills/thinking-circle-of-competence.md) — skill · 664 installs
- [doublecheck](https://affpapa.org/en/nevibecode/skills/doublecheck.md) — skill · 4300 installs
- [Guardian](https://affpapa.org/en/nevibecode/mcp/guardian.md) — MCP server · 3246 installs
- [Creed Space](https://affpapa.org/en/nevibecode/mcp/creed-space.md) — MCP server · 10491 installs
- [fact-check](https://affpapa.org/en/nevibecode/skills/jwynia-fact-check.md) — skill · 799 installs

From the same set: [qdhenry/claude-command-suite](https://affpapa.org/en/nevibecode/by/qdhenry/claude-command-suite.md) — 112 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
