A task tracker and handoff tool for AI agents working across long or multiple sessions. It keeps one main goal visible and records notes so another agent can continue the work.

Use it to track the main goal during a session and create a plain-text handoff between sessions or agents. It is intended for extended work, not short tasks completed in one pass.

Long tasks can lose their direction, and a new session may not know what has already been decided. This keeps the current objective clear and gives the next agent context to check before continuing.

throughline — Plugin by jovesun-lab

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 jovesun-lab/whetstone

agentmods

npx agentmods add plugins/jovesun-lab/whetstone/throughline

Clone the repo

git clone --depth 1 https://github.com/jovesun-lab/whetstone

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

throughline 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 2d 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.

handoff-skill/throughline/.claude-plugin/plugin.json · 19 lines

What it actually says

{
  "name": "throughline",
  "description": "Task-Track & Handoff for AI agents on long, multi-session work. Within a session it pins one ⭐️ MAIN goal (frozen title, explicit verdict at close) in an emoji-tagged task list so the agent doesn't drift; across sessions or agents it writes a plain-markdown handoff the next agent re-derives before trusting. Not for short, one-pass tasks.",
  "version": "0.2.0",
  "author": {
    "name": "arcgram.io"
  },
  "homepage": "https://github.com/jovesun-lab/whetstone/tree/main/handoff-skill/throughline",
  "repository": "https://github.com/jovesun-lab/whetstone",
  "license": "MIT",
  "keywords": [
    "handoff",
    "session-continuity",
    "task-tracking",
    "ai-agents",
    "anti-drift"
  ]
}

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.

2d ago First seen · 19 lines scan A 95bbd380af2b

Subscribe to this mod's changes

throughline is a plugin published in the GitHub repository jovesun-lab/whetstone (8 stars, last pushed 11d 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 Planning Productivity agent-skills ai-agents claude codex cursor gemini

throughline

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

ralph-loop

declared

with-bin

imagine-mcp

broken

stray