What is loom-probe-protocol?

A set of rules for responding when Loom asks an interactive terminal whether an AI agent is running there. It applies only to manually started terminal sessions, not background jobs or scheduled runs.

Use it when handling Loom terminal probes and reporting the role of the agent in an interactive session.

It makes terminal detection consistent and prevents automated jobs from waiting for a response they will never receive.

loom-probe-protocol — Skill for Claude Code and Codex by rjwalters

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.

Any agent

npx skills add rjwalters/kicad-tools --skill loom-probe-protocol

Clone the repo

git clone --depth 1 https://github.com/rjwalters/kicad-tools

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rjwalters/kicad-tools/loom-probe-protocol/github.svg)](https://agentmods.dev/skills/rjwalters/kicad-tools/loom-probe-protocol)

Your own site

<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/loom-probe-protocol"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/loom-probe-protocol/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/loom-probe-protocol"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/loom-probe-protocol.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,027 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.01027
Opus 5.5	$0.00014	$0.00411
Sonnet 5.5	$0.00007	$0.00205
Haiku 4.5	$0.00003	$0.00103

Measured 1mo ago against content hash ce46aaecdb58, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

loom-probe-protocol 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 1mo 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.

.agents/skills/loom-probe-protocol/SKILL.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.

Terminal Probe Protocol (canonical)

Loom uses an intelligent probe system to detect what's running in each terminal. When you receive a probe command, respond according to this protocol.

This is the single canonical copy of the probe protocol. Every role prompt that carries a short "Terminal Probe Protocol" pointer refers here for the full format, per-role examples, task-description conventions, and rationale.

When this protocol applies (interactive terminals only)

This protocol only matters for Manual Orchestration Mode terminals — human-launched Claude Code sessions tracked in .loom/config.json's terminals list. Those are the only sessions a terminal probe is ever sent to.

It does not apply to:

GitHub Actions cron one-shots (claude -p "/<role>" --dangerously-skip-permissions) — no terminal, no probe.
/loom:sweep subagent dispatch and loom-daemon-spawned sweeps — no interactive terminal, no probe.

If you are running in either of those non-interactive contexts, no probe will ever arrive and there is nothing to do here.

When you see this probe

# Terminal Probe: Are you an AI agent? If yes, respond with "AGENT:<role>:<primary-task>". If you're a bash shell, this is just a comment.
true

How to respond

Format: AGENT:<your-role>:<brief-task-description>

Examples:

AGENT:Builder:implementing-issue-456
AGENT:Judge:evaluating-PR-123
AGENT:Curator:enhancing-issue-456
AGENT:Champion:merging-PR-123
AGENT:Doctor:fixing-changes-requested-789
AGENT:Guide:triaging-issue-queue
AGENT:Architect:analyzing-system-design
AGENT:Hermit:scanning-for-dead-code
AGENT:Auditor:validating-main-build
AGENT:Driver:idle-awaiting-work

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.

1mo ago First seen · 95 lines · 34 tokens per session scan A ce46aaecdb58

Subscribe to this mod's changes

loom-probe-protocol is a skill published in the GitHub repository rjwalters/kicad-tools (73 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,027 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-24.

Building agents

loom-probe-protocol next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
loom-probe-protocolrjwalters/kicad-tools	Skill	73	yesterday	MIT	A	34	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	2d ago	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	today	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	315k	5d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code