Skip to main content
command CX Codex

review-gladiator — Claude Code command: what it does, how to install

review-gladiator processes recorded observations across sessions, clusters recurring patterns, and suggests actionable workflow rules.

MIT ★ 78 updated 2026-03-05

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add Vvkmnn/claude-emporium
/plugin install claude-gladiator@claude-emporium
Open on GitHub

What review-gladiator does

The command triggers batch analysis across accumulated assistant logs. It calls gladiator_reflect() to aggregate related notes into clusters and suggest concrete fixes, such as revising a rule in ~/.claude/rules/avoid.md after recurring edit failures.

Execution integrates with companion components when available. If the historian component is active, it pulls past conversations using list_recent_sessions() and logs them via gladiator_observe(). With the oracle component present, it searches existing project artifacts before suggesting fresh rules, so you avoid re-creating workflows already covered by installed plugins.

What it helps with

  • cluster recurring edit errors across long sessions
  • turn repetitive developer corrections into persistent rules
  • focus workflow reflection on a specific domain such as auth

Example prompts for the agent

  • /review-gladiator
  • /review-gladiator auth

How to install review-gladiator

1Plugin marketplace

/plugin marketplace add Vvkmnn/claude-emporium
/plugin install claude-gladiator@claude-emporium

2Manually: put the files in place

.claude/commands/review-gladiator.md

Call it with /review-gladiator. For all projects use ~/.claude/commands/

Questions about review-gladiator

How to install review-gladiator in Claude Code?

Add the marketplace and install the package by running /plugin marketplace add Vvkmnn/claude-emporium followed by /plugin install claude-gladiator@claude-emporium.

What does review-gladiator do?

It reviews past session data, runs gladiator_reflect() to cluster events, and produces suggestions for project rules or workflow adjustments.

Can review-gladiator focus on a single subject?

Yes, specify a topic argument after the command name, such as /review-gladiator auth.

Source text

review-gladiator.md · MIT
---
name: review-gladiator
description: Batch learn from session history and reflect
arguments: topic?
---

# /review-gladiator

Review accumulated observations, enrich with session history, and generate recommendations.

## Usage

- `/review-gladiator` - Reflect on all unprocessed observations
- `/review-gladiator auth` - Focus reflection on auth-related patterns

## Action

1. If **historian** sibling is active:
   - `list_recent_sessions()` to get session references
   - `gladiator_observe(source: "conversation", session_ref: <ref>)` for relevant sessions
2. Call `gladiator_reflect()` to cluster observations and generate recommendations
3. If **oracle** sibling is active:
   - Search for existing solutions before proposing new artifacts
4. Present recommendations to user with proposed changes

## When to Use

- **After a long session**: Before context is lost
- **After shipping**: Natural checkpoint to capture learnings
- **Periodically**: Every few sessions to evolve your workflow
- **After repeated errors**: When patterns emerge worth encoding

## Example Output

```
gladiator_reflect()

3 clusters found:
1. "Edit failures" (5 observations)
   → Recommendation: Add context lines to Edit calls
   → Existing rule at ~/.claude/rules/avoid.md could be updated

2. "Test-first pattern" (3 observations)
   → Recommendation: Encode TDD workflow for this project
   → 🔮 oracle found: tdd-workflows plugin (already installed)
```

© vvkmnn · MIT · Vvkmnn/claude-emporium

Similar slash commands

All slash commands for Agent setup: memory, context, orchestration →

From the same set20

The whole set →
reprompt-orator reprompt-orator rewrites a prompt with Anthropic techniques: scores it on seven dimensions, picks the fitting ones and hands back a restructured version. CX Codex +1 ★ 78repo stars search-oracle search-oracle searches across 17 sources for skills, plugins, and MCP servers. Useful when you need to discover and install new tooling directly inside Claude Code. CX Codex +1 ★ 78repo stars restore-praetorian restore-praetorian is a Claude Code command that retrieves past work from praetorian memory. It helps resume tasks by finding recent summaries or searching saved session context. CX Codex +1 ★ 78repo stars compact-praetorian compact-praetorian — a Claude Code command that writes the current session context into praetorian memory so it persists across sessions. Trigger it after research, exploration, or any decision worth keeping. CX Codex +1 ★ 78repo stars claude-oracle claude-oracle searches 17 sources for relevant skills, plugins, and MCP servers. It runs before planning and after Bash errors. CX Codex +1 ★ 78repo stars claude-praetorian claude-praetorian — a skill that snapshots your context before it gets compacted and brings it back later: before planning, after web research, when a subagent finishes. CX Codex +1 ★ 78repo stars claude-vigil claude-vigil saves file checkpoints and automatically quicksaves code before risky bash operations like rm or git reset. Roll back edits whenever an agent command goes wrong. CX Codex +1 ★ 78repo stars claude-orator claude-orator scores prompts across seven dimensions and returns a reworked version. Use it to shape subagent requests or review prompts across a session. CX Codex +1 ★ 78repo stars

Project sponsors

Companies that keep this analytics open