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.
npx agentmods add skills/lakpriya1s/agent-rack/session-sendnpx skills add lakpriya1s/agent-rack --skill session-sendgit clone --depth 1 https://github.com/lakpriya1s/agent-rackWrote 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.
[](https://agentmods.dev/skills/lakpriya1s/agent-rack/session-send)<a href="https://agentmods.dev/skills/lakpriya1s/agent-rack/session-send"><img src="https://agentmods.dev/badge/skills/lakpriya1s/agent-rack/session-send.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00015 | $0.00559 |
| Opus 5 | $0.00008 | $0.00280 |
| Sonnet 5 | $0.00003 | $0.00112 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
session-send 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 4d 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.
What it actually says
Send follow-up text to a running session via agent-rack's agent_session_send MCP tool.
Raw slash-command arguments:
$ARGUMENTS
Parsing
The first word is the sessionId; everything after it is the message to send verbatim — do
not rephrase or add to it.
Important: how follow-up works differs per agent, and so does when you may send
Check followUpMode on the session (via /agent-rack:session-status) first — it decides the
required status, and the two modes are opposites:
followUpMode |
Agents | Send when the session is | What happens |
|---|---|---|---|
live |
opencode (PTY) |
running | Text is written to the still-running process. |
resume |
claude, codex |
finished (completed) |
The agent is restarted with its own resume flag, continuing the same conversation as a new turn. Status returns to running and turnCount increases. |
none |
agy |
never | No way to rejoin that specific conversation. |
So for claude and codex, "the session isn't running any more" is not a failure — it is the
precondition. Do not treat a completed session as the end of the road; you can keep the
conversation going. Conversely, sending to a resume agent mid-turn is refused: poll
/agent-rack:session-status until it is no longer running, then send.
If followUpMode is none, do not retry or try to work around it — tell the user that this agent
cannot continue a conversation, and offer to start a new session with the follow-up as its prompt.
Execution
Call mcp__plugin_agent-rack_agent-rack__agent_session_send with sessionId and message. If it
errors about status, re-read the table above rather than retrying — a live agent needs a running
session and a resume agent needs a finished one.
Output
Confirm the message was sent. This does not return the sub-agent's reply — use
/agent-rack:session-status or /agent-rack:session-logs to see how it responded.
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.
- 4d ago First seen · 48 lines · 15 tokens per session scan A 788e101fbce8
session-send is a skill published in the GitHub repository lakpriya1s/agent-rack (0 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 559 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.
Other skills, from other repositories
cao-workflow
Author and run CAO Python workflow scripts — multi-step, parameterized, fan-out orchestrations executed by cao workflow run. Use when the user wants a repeatable multi-step job (e.g. data analysis over many files, a review pipeline, a parameterized batch). Authoring ends at a validated script file; running it is a…
aidlc-portfolio
Coordinate multiple AI-DLC workflows across repositories and Git worktrees using an evidence-backed portfolio catalog and deterministic workspace tooling. Use when initializing an AI-DLC portfolio workspace, discovering organization or business context, registering projects and dependencies, creating child intents and…
cao-plugin
Create a new CAO (CLI Agent Orchestrator) plugin. Use this skill whenever the user wants to add a plugin that reacts to CAO lifecycle or messaging events, scaffold a plugin package, understand plugin requirements, or integrate an external system (Discord, Slack, dashboards, logging, metrics) with CAO. Also use when…
agui-author
Author live dashboard UI from an agent via the emitui MCP tool. Emit one of six allow-listed components (approvalcard, choiceprompt, diffsummary, progress, metric, agentcard) with JSON props and it renders in any AG-UI client watching the fleet. Use when you want the operator to see a decision, a diff, or a status…
cao-mcp-apps
Enable, operate, and extend CAO's MCP Apps surface — the host-rendered fleet dashboard visible inside MCP App hosts (Claude Desktop, ChatGPT, VS Code Copilot, Goose, Postman). Use when the user says "enable MCP Apps in CAO", "the ui://cao views aren't rendering", "rebuild MCP Apps bundles", "add a new ui://cao/ view"…
cao-provider
Create a new CLI agent provider for CAO (CLI Agent Orchestrator). Use this skill whenever the user wants to add support for a new CLI-based AI agent (e.g., a new coding assistant CLI), integrate a new provider, or scaffold a provider implementation. Also use when the user asks about the provider architecture, what…