agent-work-protocol

A set of operating rules for coding agents covering scope, ambiguity, workflow size, and verification. A hook can load these rules automatically at session start.

In plain words
What is it for?
Use it to guide coding-agent behavior across projects and sessions.
Why use it?
It helps an agent stay within the requested scope, surface unclear requirements, and check its work before claiming completion.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add Ryuketsukami/agent-work-protocol
agentmods
npx agentmods add plugins/ryuketsukami/agent-work-protocol/agent-work-protocol
Clone the repo
git clone --depth 1 https://github.com/Ryuketsukami/agent-work-protocol

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

agent-work-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.

.claude-plugin/plugin.json · 22 lines

What it actually says

{
  "name": "agent-work-protocol",
  "version": "1.0.0",
  "description": "An always-on operating protocol for coding agents: build only what's asked, surface ambiguity as Q/A/P/E/X, scale process to task size, and verify before claiming. Injected into every session via a SessionStart hook.",
  "author": {
    "name": "Ryuketsukami",
    "url": "https://github.com/Ryuketsukami"
  },
  "homepage": "https://github.com/Ryuketsukami/agent-work-protocol",
  "repository": "https://github.com/Ryuketsukami/agent-work-protocol",
  "license": "MIT",
  "keywords": [
    "claude-code",
    "agent",
    "protocol",
    "workflow",
    "hooks",
    "agentic-coding",
    "guardrails"
  ]
}
Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 22 lines scan A 9c9aac7c0e7c

Subscribe to this mod's changes

agent-work-protocol is a plugin published in the GitHub repository Ryuketsukami/agent-work-protocol (1 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.