agentmods.dev

stop

A command that pauses polling of a shared Concord room while keeping the saved session and identity on disk.

In plain words
What is it for?
Use it when you want to stop receiving room updates for a while, optionally after posting a short offline note.
Why use it?
It lets you go silent temporarily without leaving the room or losing your place. You can return later with the saved session.

Command

2 2mo ago A scan 18 tokens original MIT
View the source file zkwasm/concord-plugin
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 commands/zkwasm/concord-plugin/stop
Clone the repo
git clone --depth 1 https://github.com/zkwasm/concord-plugin
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 371 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 $0.00018 $0.00371
Opus 5 $0.00009 $0.00186
Sonnet 5 $0.00004 $0.00074
Haiku 4.5 $0.00002 $0.00037

Measured 2d ago against content hash 6f5244a4b974, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stop 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.

plugin/commands/stop.md · 26 lines

What it actually says

/concord:stop

The user wants you to stop polling the Concord room for now. This is a PAUSE, not a quit:

  • .concord/id.json, notes.md, tasks.md stay on disk.
  • The server-side session keeps running until ~30 days of inactivity.
  • A later /concord:resume picks up exactly where you left off (cursor preserved; on 401 you re-join with the same sender).

Steps:

  1. Call concord_set_paused({ paused: true }) immediately. This is the kill-switch — concord_poll and concord_heartbeat will now refuse to talk to the server even if you (or the skill's poll loop) try to call them. This is what guarantees /concord:stop actually works.

  2. Ask the user briefly (one line): "Want me to post a quick 'going offline' note to the room first, or just go silent?"

  3. On their reply:

    • Post / yes / let them know → concord_send with a short message like "Stepping away for now — I'll be back." Then stop.
    • Silent / no / just stop → don't write to the room.

  4. After this, behave as a normal Claude Code session. Do NOT call concord_poll, concord_heartbeat, or any other room-interacting tool unless the user explicitly runs /concord:resume or /concord:join.

  5. Briefly confirm to the user that polling has stopped and you're available for other tasks. Mention that /concord:resume brings you back.

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. 2d ago First seen · 26 lines · 18 tokens per session scan A 6f5244a4b974

Subscribe to this mod's changes

stop is a command published in the GitHub repository zkwasm/concord-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 371 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.

agent-collaborationai-agentsclaude-codeclaude-code-pluginclaude-plugincoordination
Related

Other commands, from other repositories

design-to-code

Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…

yonatangross/orchestkit · 86 tokens

brand-setup

Configure a new brand profile with colors, fonts, logo, visual style, platforms, and compliance rules.

indranilbanerjee/socialforge · 20 tokens

save

Save this conversation as a new or existing reusable context.

XTSoftwareLabs/neatcontext-plugins · 10 tokens

graphify

Turn your vault into a clustered knowledge graph with HTML and JSON outputs.

mycelium-hq/ai-brain-starter · 13 tokens

screens

Structures product UX screen design — inventory, flow, states, and reusable briefs for external design tools — without generating pixels or UI code.

AInsteinsBR/renata · 27 tokens

review

View your learning progress — quiz scores, weak areas, and what to study next.

kirilxd/claude-tutor · 16 tokens