A command for registering a coding-agent session with the claude-presence coordination service. Registration records the session, project, branch, purpose, and related session details.

Use it at the start of a session to register the project and branch, provide a short intent, and associate the session with its client identifier.

It lets multiple sessions coordinate their work and identify who is working in a project. It also reports when the same client session is already registered elsewhere.

register — Command for coding agents by garniergeorges: A command for registering a coding-agent session with the…

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 commands/garniergeorges/claude-presence/register

Clone the repo

git clone --depth 1 https://github.com/garniergeorges/claude-presence

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/commands/garniergeorges/claude-presence/register.svg)](https://agentmods.dev/commands/garniergeorges/claude-presence/register)

Your own site

<a href="https://agentmods.dev/commands/garniergeorges/claude-presence/register"><img src="https://agentmods.dev/badge/commands/garniergeorges/claude-presence/register.svg" alt="Measured on agentmods" height="20"></a>

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 375 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.

Model	Per session	Once invoked
Fable 5	$0.00015	$0.00375
Opus 5	$0.00008	$0.00187
Sonnet 5	$0.00003	$0.00075
Haiku 4.5	$0.00002	$0.00038

Measured 5d ago against content hash 5b1c9bb72bc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

register 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 5d 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.

commands/register.md · 19 lines

What it actually says

Call the claude-presence MCP session_register tool with:

session_id: a short stable id for this session. Use the Claude Code session id if known, otherwise generate a short random one like s-<4 random chars>.
project: the current working directory (absolute path).
branch: the current git branch (run git rev-parse --abbrev-ref HEAD if unknown).
intent: a one-line description of what this session is doing. If the user provided arguments to this command ($ARGUMENTS), use that as the intent. Otherwise ask the user what they're working on.
pid: the Claude Code process PID if known (optional).
client_session_id: the literal value ${CLAUDE_SESSION_ID}. This lets the UserPromptSubmit hook resolve "me" from the session id Claude Code sends on stdin, so direct messages and warning/urgent broadcasts surface automatically on the next prompt without the user typing /inbox.

If the tool response is ok: false with reason: "client_session_id_conflict", it means another claude-presence session is still mapped to this Claude Code session id (typical case: previous session was not unregistered cleanly). Tell the user the held_by id from the response and suggest either /release then retry, or registering without client_session_id and accepting that auto-surfacing of notifications won't work for this session.

After registration, if other sessions are active on the same project, summarise them briefly (count, their branches, their intents) so the user is aware.

If $ARGUMENTS is non-empty, use it as the intent without asking.

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.

5d ago First seen · 19 lines · 15 tokens per session scan A 5b1c9bb72bc4

Subscribe to this mod's changes

register is a command published in the GitHub repository garniergeorges/claude-presence (12 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 375 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 2026-08-30.

Building agents claude-code cli coordination developer-tools mcp model-context-protocol

register

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

validate-dependencies

validate-prd

editorial-review-structure

add-tool

compile

OPSX: Archive