Skip to main content
skill CX Codex

claude-gladiator — Claude Code skill: what it does, how to install

claude-gladiator tracks tool failures, collects observations, and prompts reflection to update rules and skills at session end. It helps the agent learn from its own mistakes.

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 claude-gladiator does

The skill automates continuous learning by monitoring tool failures. A PostToolUse hook watches Bash, Edit, and Write executions, logging context before and after errors occur. When a session ends, the Stop hook checks for unprocessed logs and triggers a reflection prompt.

The /review-gladiator [topic] command runs batch learning across session history. Instead of generating duplicate files, it clusters observations and proposes updates to existing project artifacts. When companion plugins historian or oracle are present, it cross-references past session solutions and searches for existing tooling.

The skill depends on a separate MCP server configured via claude mcp add gladiator -- npx claude-gladiator-mcp. Without this MCP integration, observation recording and clustering cannot run.

What it helps with

  • record failure context from Bash, Edit, and Write tools
  • cluster recurring errors at session end to produce actionable advice
  • update existing instructions and skills instead of duplicating them
  • query past fixes and available tools when paired with historian or oracle

Example prompts for the agent

  • /review-gladiator build-errors
  • Run /review-gladiator to analyze recent session failures and update our guidelines
  • Cluster accumulated tool errors and propose changes to existing skills

How to install claude-gladiator

1Plugin marketplace

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

This installs the whole claude-gladiator plugin with all its skills

2Skills CLI (Vercel)

npx skills add Vvkmnn/claude-emporium --skill claude-gladiator -a claude-code

3Manually: put the files in place

~/.claude/skills/claude-gladiator/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/claude-gladiator/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about claude-gladiator

How to install claude-gladiator in Claude Code?

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

What does claude-gladiator do?

It logs failed tool executions, clusters error patterns, and recommends updates to rules, skills, or hooks at the end of sessions.

What prerequisites does claude-gladiator require?

You must register its MCP server by running claude mcp add gladiator -- npx claude-gladiator-mcp.

Source text

SKILL.md · MIT
---
name: claude-gladiator
description: Continuous learning — hooks observe failures and prompt reflection, sibling synergy deepens analysis with history and tool discovery
triggers: [PostToolUse, Stop]
---

# Gladiator Plugin

Continuous learning. Observes tool failures and prompts reflection at session end to evolve rules, hooks, and skills.

## Hooks

| Hook | When | Action |
|------|------|--------|
| **PostToolUse(Bash\|Edit\|Write)** | After tool failure | Observes the error pattern (silent on success) |
| **Stop** | Session ending | Prompts reflection if unprocessed observations exist |

## Commands

| Command | Description |
|---------|-------------|
| `/review-gladiator [topic]` | Batch learn from accumulated observations and session history |

## Workflows

### Observe (automatic via hooks)

Tool failures trigger observation automatically:
```
gladiator_observe(
  summary: "<what failed and how it was fixed>",
  context: {error, tool, before, after},
  tags: ["error", "<tool_name>"]
)
```

### Reflect (standalone)

1. `gladiator_reflect()` — cluster observations into recommendations
2. For each recommendation: read the existing artifact (if overlap detected)
3. Propose UPDATE to existing artifact, not a new duplicate
4. Present to user with reasoning
5. Apply changes one at a time after approval

### Reflect (with siblings)

1. If **historian** active: enrich reflection with broader context
   - `search_conversations("project or topic")` — related past work
   - `get_error_solutions("specific error")` — for error clusters
   - `find_tool_patterns("tool name")` — for tool workflow clusters
2. `gladiator_reflect()` — cluster observations
3. If **oracle** active: for each recommendation involving new artifacts
   - `search("cluster tag")` — check if best-in-class solution already exists
   - Install existing solution instead of reinventing
4. Present enriched recommendations: pattern + history + available tools
5. Apply changes one at a time after approval

### Batch Review (/review-gladiator)

1. If **historian** active: `list_recent_sessions()` to get session refs
2. `gladiator_observe(source: "conversation", session_ref: <ref>)` for relevant sessions
3. `gladiator_reflect()` to cluster all observations
4. If **oracle** active: search for existing solutions before creating new
5. Present recommendations to user

## Sibling Synergy

| Sibling | Value | How |
|---------|-------|-----|
| **Historian** | Past solutions enrich reflection | `get_error_solutions()`, `search_conversations()`, `find_tool_patterns()` |
| **Oracle** | Existing tools found before creating new | Search oracle for best-in-class solutions during reflection |
| **Praetorian** | n/a | Gladiator has its own persistence |
| **Vigil** | n/a | Different concerns (files vs patterns) |

## Observation Templates

| Situation | Call |
|-----------|------|
| Tool failure (auto) | `gladiator_observe(summary, context={error, tool, before, after}, tags=["error", tool])` |
| User correction | `gladiator_observe(summary, context={before, after}, tags=["correction"])` |
| Convention found | `gladiator_observe(summary, tags=["convention", "domain"])` |
| Decision made | `gladiator_observe(summary, tags=["architecture", "decision"])` |

## Requires

```
claude mcp add gladiator -- npx claude-gladiator-mcp
```

© vvkmnn · MIT · Vvkmnn/claude-emporium

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set20

The whole set →
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 claude-historian claude-historian — a skill that automatically searches past sessions before triggering web research, planning, or debugging. Reuse past solutions across projects and avoid redundant work. CX Codex +1 ★ 78repo stars claude-orator claude-orator is a Claude Code plugin that scores and restructures prompts before they go to subagents. Its hook suggests a rewrite for underspecified Task prompts. ★ 78repo stars claude-vigil claude-vigil creates file snapshots before destructive operations, shows what changed, and restores safely. Protection against accidental deletion or overwriting. ★ 78repo stars claude-gladiator claude-gladiator is a Claude Code plugin that catches tool failures and prompts reflection before sessions close. ★ 78repo stars claude-oracle claude-oracle searches 17 sources for skills, plugins, and MCP servers. It can look for relevant tools before planning or after a command error. ★ 78repo stars

Project sponsors

Companies that keep this analytics open