_template

_template is an agent for coding agents from tony/skills. It costs 0 tokens per session (1,000 once invoked), scanned A, original, MIT.

A template for documenting how a coding agent connects to and communicates with other agent sessions. It requires every unknown detail to be recorded with an explanation.

In plain words
What is it for?
Use it when adding support for a new agent, documenting identity and discovery, or describing messaging transports and limitations.
Why use it?
It gives new agent adapters a consistent structure and makes missing knowledge visible instead of leaving undocumented gaps.

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/tony/skills/_template
Clone the repo
git clone --depth 1 https://github.com/tony/skills

Wrote 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.

agentmods badge for _template

README.md
[![agentmods](https://agentmods.dev/badge/agents/tony/skills/_template.svg)](https://agentmods.dev/agents/tony/skills/_template)
Your own site
<a href="https://agentmods.dev/agents/tony/skills/_template"><img src="https://agentmods.dev/badge/agents/tony/skills/_template.svg" alt="Measured on agentmods" height="20"></a>
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 1,000 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.01000
Opus 5 $0.00000 $0.00500
Sonnet 5 $0.00000 $0.00200
Haiku 4.5 $0.00000 $0.00100

Measured today against content hash a9ffdeecdd47, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

_template 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 today.

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.

plugins/agent-messaging/references/agents/_template.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adapter:

Copy this file to a new file named for the agent, beside the existing adapters, and fill every section. Any section you cannot answer stays in the file marked UNKNOWN with a note on what you tried — a blank is a bug, UNKNOWN is data.

The skill reads adapters, never agent-specific code paths. If supporting your agent requires changing the skill rather than this file, say so under Gaps — that is a finding about the skill's design.

1. Identity

  • Own address: how a running session learns the string others use to reach it.
  • Where it is exposed: env var, slash command, status pane, file on disk.
  • Stability: does it survive a resume, a rename, a restart?
  • Human-readable name: how one is set, whether names are unique, what happens on collision.

2. Discovery

  • Enumerate peers: exact command or tool.
  • Scope: same machine only, or wider? Same home directory? Same container?
  • What a listing shows: name, id, cwd, status, liveness.
  • Blind spots: which sessions never appear, and why.

3. Transports

One block per transport this agent supports, sender side and receiver side.

  • Name (tmux / codex-queue / claude-code-message / claude-code-socket / new).
  • Direction: can this agent send on it, receive on it, or both.
  • Invocation: the exact command, tool call, or frame. Copy-pasteable.
  • Preconditions: daemon running, experimental capability, feature flag, socket bound, version floor.
  • Failure mode when the precondition is missing: verbatim error text.

4. Delivery semantics

  • When a message reaches the model: immediately, between tool calls, only when idle.
  • Latency: measured, idle and mid-turn.
  • Target not running: dropped, or durable and delivered on resume.
  • Ordering under rapid sends.
  • Caps: message size, queue depth, burst limits, and the behavior at each.
  • Interrupt interaction: what an interrupted turn does to pending messages.

Read the full file on GitHub · 95 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. today First seen · 95 lines · 0 tokens per session scan A a9ffdeecdd47

Subscribe to this mod's changes

_template is an agent published in the GitHub repository tony/skills (2 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,000 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 2026-09-03.