A command-line tool for creating and managing operator-approved groups of recipients across projects and domains. Groups control which recipients can receive shared information.

Use it to list or inspect groups, create groups, and add or remove project membership.

It provides a narrower, governed way to share information than sending it to an entire domain. Changes require an explicit confirmation before they are applied.

cm-group — Command for Claude Code by Zenetusken/consolidate-memory

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add Zenetusken/consolidate-memory

Claude Code

/plugin install consolidate-memory

Made for: Claude Code.

Or install consolidate-memory, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 1 hook.

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/zenetusken/consolidate-memory/cm-group/github.svg)](https://agentmods.dev/commands/zenetusken/consolidate-memory/cm-group)

Your own site

<a href="https://agentmods.dev/commands/zenetusken/consolidate-memory/cm-group"><img src="https://agentmods.dev/badge/commands/zenetusken/consolidate-memory/cm-group/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/commands/zenetusken/consolidate-memory/cm-group"><img src="https://agentmods.dev/badge/commands/zenetusken/consolidate-memory/cm-group.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 650 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	$0.00029	$0.00650
Opus 5.5	$0.00012	$0.00260
Sonnet 5.5	$0.00006	$0.00130
Haiku 4.5	$0.00003	$0.00065

Measured 1mo ago against content hash 95639440f7cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cm-group 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.

plugins/consolidate-memory/commands/cm-group.md · 46 lines

What it actually says

Groups are the governed successor to the old A→B layer (v0.4.10 spec docs/group-scopes.spec.md): an operator-granted recipient set that NARROWS a fact's delivery (recipients: on the canonical) and may bridge domains. A group is created in a HOME domain; membership is granted per project; a fact may target only groups born in its own domain. Read-only first:

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cm_ops.py" group list
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cm_ops.py" group show "<name>"

Plan-first mutations (each needs its exact confirm phrase — the confirmation IS the grant):

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cm_ops.py" group create "<name>" --domain "<home>"
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cm_ops.py" group create "<name>" --domain "<home>" --apply --confirm create-group-"<name>"
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cm_ops.py" group add "<name>" "<project-path>"
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cm_ops.py" group add "<name>" "<project-path>" --apply --confirm add-group-"<name>"
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cm_ops.py" group remove "<name>" "<project-path>"
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cm_ops.py" group remove "<name>" "<project-path>" --apply --confirm remove-group-"<name>"
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cm_ops.py" group delete "<name>"
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cm_ops.py" group delete "<name>" --apply --confirm delete-group-"<name>"

group add across domains IS allowed — the operator declares the bridge. group remove withdraws the member's group mirrors: clean mirrors are deleted, locally-edited ones quarantined (never lost) — and that revoke precedes any later delete decision (the two-step protects the delete, not the revoke). group delete refuses a populated group (remove the members first — the refusal names them; a registry-only member on another machine has no local path to remove through the CLI, so use the phantom-path convention: a local path for that project) and prints the citation count first: facts whose recipients: name the group will deliver to nobody after the delete — re-point or forget them before confirming. A recreated group name is a fresh identity — facts whose recipients predate it refuse to re-point unless re-confirmed (--repoint on cm canonical upsert, or sync_global.py --promote … --repoint); the pull side withholds stale delivery per-recipient, and gc reclaims the stranded mirrors (clean deleted, locally-edited quarantined).

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 Changed 95639440f7cb
2mo ago First seen · 46 lines · 29 tokens per session scan A 9055c6472ca1

Subscribe to this mod's changes

cm-group is a command published in the GitHub repository Zenetusken/consolidate-memory (7 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 650 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 2026-09-05.

Claude Code Memory and context Project management ai-agents claude-code-plugin context-management

cm-group next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cm-groupZenetusken/consolidate-memory	Command	7	1mo ago	MIT	A	29	Claude Code
remembrall-helpcukas/remembrall	Command	6	3d ago	MIT	A	17	Claude Code
budgetcukas/remembrall	Command	6	3d ago	MIT	A	13	Claude Code
handoffse4thvin/context-handoff	Command	1	5mo ago	MIT	A	14	Claude Code
recall-maintaindavegoldblatt/total-recall	Command	202	8mo ago	none	A	0	Claude Code
recall-init-idsdavegoldblatt/total-recall	Command	202	8mo ago	none	A	0	Claude Code
recall-initdavegoldblatt/total-recall	Command	202	8mo ago	none	A	0	Claude Code