Version: 1.0.0 Protocol Version: 2024-11-05 Last Updated: 2026-01-10
R. Mathieu Landvreugd rmlandvreugd
SamSaffron
/ CLAUDE_AGENT_SDK_SPEC.md
Created
January 10, 2026 00:42
cameroncooke
/ AGENTS.md
Created
December 30, 2025 11:29
My global agents file tailed for self-improvement
- Address the user as Cam.
- Optimize for correctness and long-term leverage, not agreement.
- Be direct, critical, and constructive — say when an idea is suboptimal and propose better options.
- Assume staff-level technical context unless told otherwise.
- Inspect project config (
package.json, etc.) for available scripts.
Here's my AGENTS.md (also linked from CLAUDE.md as @AGENTS.md) for hacking
agentically on MDFlow recipes.
I have this in ~/.mdflow/, and the agents/recipes live in ~/.mdflow/agents/ and added to the path
so that they can be invoked as commands.
With this I can use a coding agent like Claude Code or GitHub Copilot in VSCode and say something like:
> create a new agent using copilot that reviews all the code files in this directory as a poem
spenceriam
/ AGENTS.md
Last active
January 19, 2026 10:21
— forked from Xuanwo/AGENTS.md
Xuanwo's AGENTS.md (converted to English)
- The person you are assisting is User.
- Assume User is an experienced senior backend/database engineer, familiar with mainstream languages and their ecosystems such as Rust, Go, and Python.
- User values "Slow is Fast", focusing on: reasoning quality, abstraction and architecture, long-term maintainability, rather than short-term speed.
- Your core objectives:
- As a strong reasoning, strong planning coding assistant, provide high-quality solutions and implementations in as few interactions as possible;
- Prioritize getting it right the first time, avoiding superficial answers and unnecessary clarifications.
Applied rationality for a coding agent. Defensive epistemology: minimize false beliefs, catch errors early, avoid compounding mistakes.
This is correct for code, where:
- Reality has hard edges (the compiler doesn't care about your intent)
- Mistakes compound (a wrong assumption propagates through everything built on it)
- The cost of being wrong exceeds the cost of being slow
alirezarezvani
/ claude-code-skills-complete-guide.md
Last active
January 20, 2026 09:40
Ultimate guide to extending Claude Code with skills, agents, commands, and utilities. Covers Tresor (ready-to-use), Skill Factory (custom builds), and Skills Library (26+ domain packages).
Ultimate resource for extending Claude Code with custom skills, specialized agents, slash commands, and professional utilities
Last Updated: October 28, 2025 | Author: Alireza Rezvani | License: MIT
Claude Flow treats memory as the backbone and MCP tools as the hands. You get concurrent agents that coordinate cleanly, keep context tight, and ship durable artifacts without dragging long text through prompts. It feels like an ops layer for intelligence.
The stack is simple. Claude Code as the client. Claude Flow as the MCP server. SQLite memory at .swarm/memory.db for state, events, patterns, workflow checkpoints, and consensus. Artifacts hold the big payloads. Manifests in memory link everything with ids, tags, and checksums.
Coordination is explicit. Agents write hints to a shared blackboard, gate risky steps behind consensus, and record every transition as an event. Hooks inject minimal context before tools run and persist verified outcomes after. Small bundles in, durable facts out.
Planning keeps runs stable. Use GOAP to sequence actions with clear preconditions. Use OODA to shorten loops.
Observe metrics, orient with patterns, decide through votes, act with orchestration. Topology adapts from hi
NewerOlder