By chetmancini
Self-tuning feedback loop for Claude Code, Gemini CLI, Codex, and OpenCode. Collects session metrics, analyzes patterns, and produces tuning recommendations to improve agent reliability and autonomy.
Analyze session metrics quickly using the local raw report only.
Analyze session metrics and produce tuning recommendations for agent configurations.
Refresh the latest schema for the active agent, compare it against the current configuration, and produce an implementation plan for new features to adopt and deprecated settings to remove.
Refresh the latest schema for the active agent, compare it against the installed config, and produce an implementation plan for new features to adopt or deprecated settings to remove. Use when asked to review schema updates, upgrade settings, leverage new schema features, deprecate old settings, or turn schema drift into an actionable implementation plan.
Validate the installed agent config against the latest schema, surface new features to adopt, and flag deprecated config to remove. Use when asked to validate settings, check schema, update schemas, verify configuration files, or review config for new/deprecated options.
Analyze Agent Smith session metrics and produce tuning recommendations for Claude Code, Codex, OpenCode, or Pi. Use when asked to analyze metrics, tune config, review agent performance, generate a performance report, or optimize agent settings.
Matches all tools
Hooks run on every tool call, not just specific ones
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
"Never send a human to do a machine's job." Agent Smith, The Matrix (1999)
Agent configuration is hard, fragile, and always changing. Agent Smith outsources that tuning work to your agent: it gathers empirical data from watching real sessions and recommends concrete changes to prompts, settings, and workflow.
Get a feedback loop based on how Claude Code, Codex, Gemini CLI, OpenCode, Pi, or Grok actually behave on your real work instead of guessing what might help.
Agent Smith:
>=1.3.0jqsqlite3python3claude plugins marketplace add chetmancini/agent-smith
claude plugins install agent-smith@agent-smith
Install from a local clone:
bun run ./agent-smith-app/src/cli.ts install-codex
Or:
make codex-install
Then:
Agent Smith.make app-doctor.The installer enables features.codex_hooks = true, links the plugin into ~/.codex/plugins/agent-smith, and configures the personal marketplace entry. The checkout still needs to stay trusted so Codex can load the repo-local .codex/hooks.json.
Gemini currently ships as a local-checkout hook extension:
gemini extensions link ./gemini-extension
This reuses the shared repo-root shell hooks and scripts.
Add Agent Smith to opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"plugin": ["agent-smith-opencode"]
}
For a local checkout instead of the published package:
{
"plugin": ["./path/to/agent-smith/opencode-plugin"]
}
Install from a local clone:
bun run ./agent-smith-app/src/cli.ts install-pi
Or:
make pi-install
Then:
make app-doctor.The installer adds this checkout to ~/.pi/agent/settings.json so Pi can discover Agent Smith from any working directory. The installed package exposes:
.pi/extensions/agent-smith/index.ts for telemetry and slash-command aliasescommands/ as prompt templatesskills/ as Agent SkillsGrok uses a plugin + project .grok/ files for hooks (telemetry) and skills (analysis commands).
Install from a local clone:
bun run ./agent-smith-app/src/cli.ts install-grok
Or:
make grok-install
Then:
/hooks-trust / use the hooks modal).make app-doctor.The installer runs grok plugin install ./grok-plugin --trust (or prints the equivalent if the grok binary is not on PATH). This registers:
grok-scoped session/tool events (reusing the shared shell emitters)./analyze-config, /upgrade-settings, etc. (also available via project .grok/skills/ when your working directory is inside this checkout).The repo also provides .grok/hooks/hooks.json and .grok/skills/ directly for pure project-scoped use (no plugin registration required when cwd is the agent-smith tree).
| Surface | Claude Code | Gemini CLI | Codex | OpenCode | Pi | Grok |
|---|---|---|---|---|---|---|
| Install path in this repo | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
agent-smith doctor coverage | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Slash commands | ✓ | ✓ | ✓ | ✓ | (skills) | |
| Shared shell commands | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Feature | Claude Code | Gemini CLI | Codex | OpenCode | Pi | Grok |
|---|---|---|---|---|---|---|
| Session lifecycle | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Bash failure tracking | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Vague prompt guidance | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Rollup and analysis | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Schema validation | ✓ | ✓ | ✓ | ✓ | ✓ | (stub) |
| Tool failures | ✓ | ✓ | ✓ | ✓ | ✓ | |
| Permission denials | ✓ | ✓ | ✓ | (via PreToolUse) | ||
| Permission grants | ✓ | |||||
| Session errors | ✓ | ✓ (Stop) | ||||
| File-edited telemetry | ✓ | ✓ (PostToolUse) | ||||
| Context compression | ✓ | ✓ | ✓ | ✓ | ✓ (PreCompact) | |
| Edit-triggered test-loop detection | ✓ | ✓ | ✓ | ✓ | ✓ | |
| Subagent lifecycle | ✓ | ✓ | ✓ | ✓ |
npx claudepluginhub chetmancini/agent-smith --plugin agent-smithComplete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Open-source, local-first Claude Code plugin for token reduction, context compression, and cost optimization using hybrid RAG retrieval (BM25 + vector search), reranking, AST-aware chunking, and compact context packets.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.