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 skills add agentproto/ts --skill ap-prompt-agentgit clone --depth 1 https://github.com/agentproto/tsWrote 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/agentproto/ts/ap-prompt-agent)<a href="https://agentmods.dev/skills/agentproto/ts/ap-prompt-agent"><img src="https://agentmods.dev/badge/skills/agentproto/ts/ap-prompt-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/agentproto/ts/ap-prompt-agent"><img src="https://agentmods.dev/badge/skills/agentproto/ts/ap-prompt-agent.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00083 | $0.01447 |
| Opus 5.5 | $0.00033 | $0.00579 |
| Sonnet 5.5 | $0.00017 | $0.00289 |
| Haiku 4.5 | $0.00008 | $0.00145 |
Grade A, and why
ap-prompt-agent scanned grade A with 1 finding 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 19d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://127.0.0.1:18790/sessions/sess_5f9a3c38/prompt \ How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt a Live Agent Session
When to use
You already have a running session (from ap-spawn-agent) and need to send
it more instructions, redirect it mid-turn, change its model/effort/posture
on the fly, or manage a backlog of prompts queued while it was busy.
MCP tool: agent_prompt
{
"tool": "agent_prompt",
"args": {
"sessionId": "sess_5f9a3c38",
"prompt": "Also add a changelog entry for the validation fix.",
"interrupt": false
}
}
By default, interrupt:false and a prompt sent while the session is
mid-turn is queued (FIFO) and dispatched automatically once the current
turn ends — fan-in bursts are delivered in order instead of rejected. Pass
interrupt:true to cancel the in-flight turn and redirect the same session
immediately instead of waiting for the queue:
{
"tool": "agent_prompt",
"args": {
"sessionId": "sess_5f9a3c38",
"prompt": "Stop — scope changed, only fix the email check, skip the password change.",
"interrupt": true
}
}
Prompt or message?
agent_prompt DRIVES a session (it's a delegation action). To talk to a
tree neighbour — answer your child's blocker, send your parent a result —
send a typed message instead: the daemon attests you as the sender, the
recipient sees it as an <agentproto-message> block (never as the user),
and it's routed by urgency.
{ "tool": "message_send", "args": { "to": "sess_5f9a3c38", "text": "Use branch main.", "kind": "report" } }
{ "tool": "message_reply", "args": { "replyTo": "msg_3f2a91c0", "text": "Approved — go ahead." } }
{ "tool": "message_parent", "args": { "message": "Tests pass, PR opened.", "kind": "done" } }
| urgency | busy recipient gets it… |
|---|---|
fyi |
inbox only (no wake) |
next-turn (default for report/done/notice) |
as its own turn when the current one ends |
steer (default for blocker/question) |
injected into its running turn, if its agent supports steering (steering: true in session_list) — else next-turn |
interrupt |
cancels its turn — only if the operator allows it (defaults.messaging.agentInterrupt), else steer |
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.
- 19d ago Changed · +25 lines e0f9f6a22304
- 1mo ago Changed · +3 lines 0e931fa57ba3
- 1mo ago First seen · 96 lines · 83 tokens per session scan A f690ed68d9e1
ap-prompt-agent is a skill published in the GitHub repository agentproto/ts (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 83 tokens to every session and 1,447 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
skill-creator-primer
You MUST load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill. Triggers include creating, editing, reviewing, or contributing to any part of an Agent Skill (description, frontmatter, body, references, scripts, trigger evals, conflicts, etc).
llm-wiki
Use when building or maintaining a self-contained personal knowledge base (an LLM wiki) in plain markdown. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki health, auditing article claims against their sources, critiquing a wiki source's reasoning, superseding stale knowledge, 'add to…
extract-wisdom
Extract wisdom, insights, and actionable takeaways from YouTube videos, blog posts, articles, or text files. Use when asked to extract wisdom or key insights from a given content source.
apply-mantel-styles
Provides guidelines for applying Mantel's brand styles to diagrams and frontend components. Use when asked to create visuals that need to align with Mantel's branding.
home-assistant
This skill should be used when helping with Home Assistant setup, including creating automations, modifying dashboards, checking entity states, debugging automations, and managing the smart home configuration. Use this for queries about HA entities, YAML automation/dashboard generation, or troubleshooting HA issues.
deepeval
Use when discussing or working with DeepEval (the python AI evaluation framework).