index

A read-only view of coding-agent activity in each terminal, including whether an agent is working, idle, or has stopped, plus a resume command when available.

In plain words
What is it for?
Watching agent activity, detecting dead sessions, showing resume commands, tracking unfinished work, and acknowledging completed runs.
Why use it?
It helps users see what agents are doing and recover sessions that ended unexpectedly without requiring agents to register themselves.

Agent

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 agents/silo-code/silo/index
Clone the repo
git clone --depth 1 https://github.com/silo-code/silo
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 569 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 $0.00000 $0.00569
Opus 5 $0.00000 $0.00284
Sonnet 5 $0.00000 $0.00114
Haiku 4.5 $0.00000 $0.00057

Measured yesterday against content hash cd7922223603, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

index 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.

apps/docs/api/agents/index.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ctx.agents

Host-computed coding-agent activity and resume-identity observability — a live, read-only view of what each terminal's agent is doing, plus an honest resume hint when a session's backend dies uncleanly. The companion to ctx.processes (foreground process facts); this surface is for agent activity and resume identity. Detection is sealed in the host — there is no registerAgent / detector API.

ctx.agents: AgentsService

Example

Notify when a session dies with a resume command

export const extension: Extension = {
  id: "my.agent-resume-toast",
  activate(ctx) {
    const sub = ctx.agents.subscribe((agents) => {
      const dead = agents.find((a) => a.activity === "dead" && a.resumeCommand);
      if (dead) ctx.ui.notify("info", dead.resumeCommand!);
    });
    ctx.subscriptions.push(sub);
  },
};

Acknowledge finished runs when the user looks at the terminal

needsAttention is separate from activity === "idle". The host never auto-clears attention on focus — that is a per-consumer policy:

ctx.subscriptions.push(
  ctx.terminals.subscribeActive((terminalId) => {
    if (terminalId) ctx.agents.acknowledge(terminalId);
  }),
);

What you get

Field Meaning
activity none | working | idle | error | dead
needsAttention Sticky "finished while you weren't looking" — cleared only by acknowledge
sessionId / resumeCommand Exact resume when a Settings → Agents hook (or native session file) resolved an id; otherwise an honest session-id-less note. Silo never infers an id from cwd/recency.
agentId / agentName Catalog key + display name once a known agent leader is detected

Read the full file on GitHub · 61 lines

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 · 61 lines · 0 tokens per session scan A cd7922223603

Subscribe to this mod's changes

index is an agent published in the GitHub repository silo-code/silo (53 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 569 tokens. 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 2026-08-30.