_agent-protocol

_agent-protocol is an agent for coding agents from samibs/skillfoundry. It costs 0 tokens per session (3,970 once invoked), scanned A, original, MIT.

A standard message format and startup sequence for agents working together in the SkillFoundry framework.

In plain words
What is it for?
Use it to structure agent communication, synchronize shared knowledge, and pass task status between pipeline stages.
Why use it?
Consistent messages make handoffs, failures, and session state easier to understand across different agents and platforms.

Agent

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 agents/samibs/skillfoundry/_agent-protocol
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

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-protocol

README.md
[![agentmods](https://agentmods.dev/badge/agents/samibs/skillfoundry/_agent-protocol.svg)](https://agentmods.dev/agents/samibs/skillfoundry/_agent-protocol)
Your own site
<a href="https://agentmods.dev/agents/samibs/skillfoundry/_agent-protocol"><img src="https://agentmods.dev/badge/agents/samibs/skillfoundry/_agent-protocol.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,970 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 $0.00000 $0.03970
Opus 5 $0.00000 $0.01985
Sonnet 5 $0.00000 $0.00794
Haiku 4.5 $0.00000 $0.00397

Measured yesterday against content hash c07fd0294caf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

_agent-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 yesterday.

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/_agent-protocol.md · 597 lines

How it starts

The opening of the file, as written. The whole thing — 597 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Communication Protocol

INCLUDE IN ALL AGENT PERSONAS This module defines the standard communication protocol for inter-agent messaging.


Overview

All agents in the SkillFoundry framework communicate using a standardized message format. This ensures:

  • Predictable handoffs between agents
  • Token-efficient communication
  • Clear accountability and traceability
  • Proper error propagation
  • Cross-platform session continuity

Session Boot Sequence

Every agent session MUST begin with:

0. Hub Sync — Pull (if configured, silent, non-blocking)
   ├── Check: does .claude/hub.json exist in the framework directory?
   │   ├── YES: Run `knowledge-sync.sh pull` (silently, in background)
   │   │        This pulls latest knowledge lessons from the hub.
   │   │        Failures are ignored — offline-first, never gate on hub.
   │   └── NO:  Skip. Framework works identically without hub.
   └── Note: Do NOT pull scratchpads from hub here.
             Local scratchpad is the authority for this machine.
             Hub scratchpads are for explicit cross-machine requests only.

1. Check .claude/scratchpad.md exists
   ├── YES: Read it. Orient to current task, phase, progress.
   │        If platform differs from last update → note platform switch.
   │        If >24h old → verify file state before trusting progress.
   │        Announce: "Continuing from [task] — [phase] — [platform]"
   └── NO:  Fresh session. Create scratchpad after first major action.

2. Check .claude/state.json exists (for /go executions)
   ├── YES: Cross-reference with scratchpad.
   │        state.json = structured "what", scratchpad = human-readable "why"
   └── NO:  Not a /go execution, scratchpad alone is sufficient.

3. Proceed with task.

This boot sequence enables seamless cross-platform continuity. When a user hits the context limit in Claude Code and switches to Copilot CLI, the new session reads the scratchpad and continues without asking "what were you working on?"

Read the full file on GitHub · 597 lines

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. yesterday First seen · 597 lines · 0 tokens per session scan A c07fd0294caf

Subscribe to this mod's changes

_agent-protocol is an agent published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,970 tokens. 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 2026-09-03.