Instructions file
Instructions for russelleNVy/three-man-team, covering three man team — session router, token rules — always active, session start — every role and reference files — on demand only.
655 tagged agent-workflow, measured the same way as everything else here.
Instructions file
Instructions for russelleNVy/three-man-team, covering three man team — session router, token rules — always active, session start — every role and reference files — on demand only.
Plugin Claude Code
Claude Code harness for routing requests, preserving run state, enforcing hooks, and recording evidence.
MCP server Claude CodeCodexCursor +2
MCP server "citadel-state" as configured in SethGammon/Citadel. Runs mcp-servers/citadel-state/index.js with node. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
MCP server "codebase-memory" as configured in SethGammon/Citadel. Runs mcp-servers/codebase-memory/index.js with node. Needs 1 environment variable to run.
Instructions file CodexOpenCode
Instructions for SethGammon/Citadel, covering codex harness, what this is, key conventions, testing and review guidelines.
Instructions file
Instructions for SethGammon/Citadel, covering claude harness, what this is, key conventions, testing and campaign design principles.
Agent
Strong-tier, different-family, adversarial, ACTING judge with FINAL veto on holistic acceptance. Unlike the lightweight phase-validator (which reads a HANDOFF and checks exit-condition prose), the arbiter re-runs the objective gates itself (typecheck, tests, lint, the phase's command conditions) and judges holistic…
Agent
Parallel campaign orchestrator. Runs multiple campaigns in coordinated waves within a single session. Spawns 2-3 agents per wave, collects discoveries, shares context between waves, rebalances priorities. Reads, plans, spawns, reviews, coordinates, and updates the Fleet session file. Source code changes belong to…
Agent
Lightweight handoff validator. Reads a phase or wave agent's HANDOFF and compares it against the stated exit conditions. Returns a structured verdict (pass/fail) with specific reasons. Never modifies files — read-only judge. Spawned by Archon after each phase and by Fleet after each wave agent.
Skill Claude CodeCodex
Autonomous multi-session campaign agent. Decomposes large work into phases, delegates to sub-agents, reviews output, and maintains campaign state across context windows. Use for work that spans multiple sessions and needs persistent state, quality judgment, and strategic decomposition.
Skill Claude CodeCodex
Parallel campaign orchestrator. Runs multiple campaigns in coordinated waves within a single session. Spawns 2-3 agents per wave in isolated worktrees, collects discoveries, shares context between waves. Use when work decomposes into 3+ independent streams that can run simultaneously.
Skill Claude CodeCodex
First-run experience for the harness. Three modes: Recommended (guided, 3 min), Full Tour (guided + skill walkthrough, 8 min), and Express (zero questions, 30 sec). Installs hooks first, detects stack, configures harness.json, runs a live demo on real code, and prints a reference card.
Instructions file CodexOpenCode
Repository instructions for coding agents working on a shared AI-work-system project. They describe how to preserve the project's structure, protect private information, and verify changes.
Instructions file
Project-specific instructions for QuietHarness, a lightweight AI work system shared by Claude Code, Codex, and Cursor. They point contributors to the project instructions and its installable personal template.
Cursor rule
QuietHarness baseline.
BrowserOperator/browser-operator-core
Instructions file
Instructions for BrowserOperator/browser-operator-core, covering claude.md, project overview, build & development commands, initial setup and build.
Instructions file CodexOpenCode
A set of project instructions for whitelonng/mancode, covering agent guidance, commands, module routing, change rules, and startup steps.
Instructions file CodexOpenCode
Instructions for byteseek/Mira, covering mira agent guide, read order, fast paths, research rules and expected artifacts.
Instructions file
Instructions for byteseek/Mira: This repository is the Mira market-research workspace.
Agent
Agent "research-orchestrator" from byteseek/Mira, covering research orchestrator agent, responsibilities, research loop, industry concept rule and monitoring loop.
Skill Claude CodeCodex
Analyze commodity cycles, futures curves, inventories, cost curves, policy/geopolitics, positioning, and transmission into related assets.
Skill Claude CodeCodex
Analyze earnings releases, filings, transcripts, guidance, peer comparisons, market reaction, and thesis impact for a company reporting event.
Skill Claude CodeCodex
Discover listed, pending, filed, or newly announced ETFs and create a structured candidate watchlist for ETF listing analysis.
Skill Claude CodeCodex
This repository ships two language-specific variants of the same skill package.
At most 3 mods per repository are shown here — the rest are on their repository pages: