A phase gate for coding-agent workflows that uses shell checks to decide whether a step passed. It keeps the workflow state and routes the agent to advance, retry, escalate, or finish.

Use it to control multi-step coding tasks with deterministic checks and explicit next actions.

It prevents the language model from deciding on its own whether work is complete. Failed checks can send the agent back for another attempt or to a human.

headsign — Plugin by meganemura

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 meganemura/headsign

agentmods

npx agentmods add plugins/meganemura/headsign/plugin

Clone the repo

git clone --depth 1 https://github.com/meganemura/headsign

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

headsign 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.

plugin/.claude-plugin/plugin.json · 24 lines

What it actually says

{
  "name": "headsign",
  "version": "0.10.0",
  "description": "A tiny phase gate for coding agents: your shell checks decide pass/fail (never the LLM), your workflow routes the agent (advance / retry / escalate / done). The agent drives, headsign holds the state.",
  "author": {
    "name": "meganemura",
    "url": "https://github.com/meganemura"
  },
  "homepage": "https://github.com/meganemura/headsign",
  "repository": "https://github.com/meganemura/headsign",
  "license": "MIT",
  "keywords": [
    "claude-code",
    "claude-code-plugin",
    "coding-agent",
    "phase-gate",
    "workflow",
    "state-machine",
    "cli",
    "loop-engineering",
    "graph-engineering"
  ]
}

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.

yesterday First seen · 24 lines scan A 3f819ba8162a

Subscribe to this mod's changes

headsign is a plugin published in the GitHub repository meganemura/headsign (1 stars, last pushed 3d 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.

Data and AI Productivity agentic-coding ai-agents claude-code claude-code-plugin cli coding-agent

headsign

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

the-loop

claude-bestpractice

ooda-loop

agent-evolutions

claude-therapy

superpowers-gstack