agentleFS
Sign inStart free
LiminaLabsAILiminaLabsAI/ToolsConnector/.agents/skills/agent_session_protocol/SKILL.md

Agent Session Protocol

Skill1 starsChanged 7 months agoApache-2.0View on GitHub

Defines the state management and cross-agent handoff protocol for ToolsConnector.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read Core Instructions: Check CLAUDE.md (or gemini.md) and /plan/brainstorm.md to understand context.

    line 12
  2. Very specific:

    Assess Project State: Read .project_state.json to identify the current active phase and outstanding issues.

    line 13
  3. Very specific:

    Adopt Persona: If the state mandates architecture design, assume the principal_architect role.

    line 14
  4. Distinctive:

    When an agent tackles a large task, they should break it down for their subagent processes:

    line 17
  5. Distinctive:

    Before terminating a session, you MUST:

    line 23
  6. Very specific:

    Update .project_state.json with what was completed.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Agent Session Protocol Skill

Overview

To function as an effective AI Agent Team (and not just isolated tools), all agents (Claude, Gemini, Cursor) must follow a strict session/handoff protocol. This ensures that the Principal Architect can pass context to the Connector Implementer without losing the thread.

Session Startup Sequence

  1. Read Core Instructions: Check CLAUDE.md (or gemini.md) and /plan/brainstorm.md to understand context.
  2. Assess Project State: Read .project_state.json to identify the current active phase and outstanding issues.
  3. Adopt Persona: If the state mandates architecture design, assume the principal_architect role. If executing a tool wrapping, assume the connector_implementer role.

Cross-Agent Subagent Coordination

When an agent tackles a large task, they should break it down for their subagent processes:

  1. The Principal Architect drafts the API shape in a scratchpad or .project_state.json.
  2. The executing agent runs generation iteratively.
  3. The Health Watcher (or Verifier) validates the implementation against the rules.

Output Discipline

Before terminating a session, you MUST:

  • Update .project_state.json with what was completed.
  • Define the remaining blockers or the next phase for the next agent session.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free