Agent Session Protocol

Agent Session Protocol is a skill for Claude Code, Codex from sachinshelke/ToolsConnector. It costs 18 tokens per session (306 once invoked), scanned A, original, Apache-2.0.

A set of rules for managing work between coding agents such as Claude, Gemini, and Cursor. It records project state, assigns roles, and defines what must be handed over between sessions.

In plain words
What is it for?
It is for coordinating architecture work, implementation, subagents, health checks, and cross-agent handoffs in a shared project.
Why use it?
It reduces lost context when different agents or sessions work on the same project. It also makes unfinished work and verification steps visible before a session ends.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/sachinshelke/toolsconnector/agent_session_protocol
Any agent
npx skills add sachinshelke/ToolsConnector --skill agent_session_protocol
Clone the repo
git clone --depth 1 https://github.com/sachinshelke/ToolsConnector

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for Agent Session Protocol

README.md
[![agentmods](https://agentmods.dev/badge/skills/sachinshelke/toolsconnector/agent_session_protocol.svg)](https://agentmods.dev/skills/sachinshelke/toolsconnector/agent_session_protocol)
Your own site
<a href="https://agentmods.dev/skills/sachinshelke/toolsconnector/agent_session_protocol"><img src="https://agentmods.dev/badge/skills/sachinshelke/toolsconnector/agent_session_protocol.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 306 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.00306
Opus 5 $0.00009 $0.00153
Sonnet 5 $0.00004 $0.00061
Haiku 4.5 $0.00002 $0.00031

Measured 5d ago against content hash b7ee4fdc2987, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

Agent Session Protocol scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/agent_session_protocol/SKILL.md · 26 lines

What it actually says

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.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 26 lines · 18 tokens per session scan A b7ee4fdc2987

Subscribe to this mod's changes

Agent Session Protocol is a skill published in the GitHub repository sachinshelke/ToolsConnector (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 18 tokens to every session and 306 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

add-test

Use when adding unit or integration tests. Provides test patterns, naming conventions, and fixtures for Python (pytest), TypeScript (vitest), Java (JUnit/Mockito), and Rust.

open-metadata/ai-sdk · 40 tokens

validate-docs

Use when reviewing or validating documentation. Checks for clarity, completeness, broken links, undefined terms, and ensures beginners can follow guides without prior knowledge of the SDK.

open-metadata/ai-sdk · 36 tokens

add-sdk-method

Use when adding a new method, function, or API endpoint to the SDK. Ensures consistent implementation across all SDKs (Python, TypeScript, Java, Rust CLI) with proper types, tests, and naming conventions.

open-metadata/ai-sdk · 49 tokens

debug-ci

Use when CI/CD pipeline fails. Provides systematic diagnosis for lint, type, test, and build failures across Python, TypeScript, Java, Rust, and n8n SDKs.

open-metadata/ai-sdk · 40 tokens

run-integration

Use when running integration tests against a real Metadata instance. Guides setup of environment variables (AISDKHOST, AISDKTOKEN) and runs tests that make actual API calls.

open-metadata/ai-sdk · 40 tokens

dignified-python

Load ONLY for Python code Use when writing, reviewing, or refactoring Python to ensure adherence to LBYL exception handling patterns, modern type syntax (list[str], str | None), pathlib operations, ABC-based interfaces, absolute imports, and explicit error boundaries at CLI level. Also provides production-tested code…

open-metadata/ai-sdk · 92 tokens