agentmods.dev

cm-connect

cm-connect is a command for coding agents from Zenetusken/consolidate-memory. It costs 38 tokens per session (570 once invoked), scanned A, original, MIT.

A command for connecting two repositories to a shared memory store. It checks both repositories, asks for explicit permission to enroll them, and can transfer a shared fact between them.

In plain words
What is it for?
Use it to inspect enrollment status, plan and confirm access for both repositories, and complete cross-project memory setup.
Why use it?
It prevents repositories from being connected or changing domains without the operator's approval. It also makes partial setup recoverable instead of silently overwriting state.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the consolidate-memory plugin — 1 skill, 8 commands, 1 hook shipped together

not rated 6 today A scan 38 tokens original MIT
View the source file Zenetusken/consolidate-memory
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/zenetusken/consolidate-memory/cm-connect
Clone the repo
git clone --depth 1 https://github.com/Zenetusken/consolidate-memory

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.

agentmods badge for cm-connect

README.md
[![agentmods](https://agentmods.dev/badge/commands/zenetusken/consolidate-memory/cm-connect.svg)](https://agentmods.dev/commands/zenetusken/consolidate-memory/cm-connect)
Your own site
<a href="https://agentmods.dev/commands/zenetusken/consolidate-memory/cm-connect"><img src="https://agentmods.dev/badge/commands/zenetusken/consolidate-memory/cm-connect.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 570 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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.00570
Opus 5 $0.00019 $0.00285
Sonnet 5 $0.00008 $0.00114
Haiku 4.5 $0.00004 $0.00057

Measured today against content hash 424b1758f06d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cm-connect 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/consolidate-memory/commands/cm-connect.md · 52 lines

What it actually says

The two-repo onboarding wizard (see docs/cm-commands-onboarding.spec.md). Enrollment is an OPERATOR grant (ADR 008) — this command sequences the grants, never self-grants; every enrollment is planned and confirmed.

  1. Survey (read-only). Doctor both repos and show the plan — enrolled? domain? — plus each enrollment's forecast (how many unadmitted mirrors it would quarantine; quarantine is recoverable, never delete):

    python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cm_ops.py doctor .
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cm_ops.py doctor <other-repo>

  2. Grants. For each unenrolled repo, show its plan and ask the user for ONE confirmation covering both. Apply each with its exact phrase (the confirmation is the grant):

    python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cm_ops.py project enroll . --domain personal --apply --confirm enroll-personal
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cm_ops.py project enroll <other-repo> --domain personal --apply --confirm enroll-personal

    A repo enrolled in a DIFFERENT domain is never auto-switched — point at move-domain. A failed second enroll leaves a valid partial state; re-running this command completes it (enroll is idempotent).

  3. Share (optional). Ask for one claim sentence; if given, run /cm-share from this repo. Skip cleanly with "link only".

  4. Absorb. Pull + harvest in BOTH repos — each picks up the domain facts it was missing:

    python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sync_global.py --list .
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sync_global.py --pull .
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sync_global.py --harvest .
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sync_global.py --pull <other-repo>
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sync_global.py --harvest <other-repo>

  5. Payoff. Show the network view — the links made:

    python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sync_global.py --tokens .
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sync_global.py --network .
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 · 52 lines · 38 tokens per session scan A 424b1758f06d

Subscribe to this mod's changes

cm-connect is a command published in the GitHub repository Zenetusken/consolidate-memory (6 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 570 once invoked, about $0.0002 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 2026-09-05.

Git and workflowMemory and contextai-agentsclaude-codeclaude-code-plugincontext-management
Related

Other commands, from other repositories

remember

Explicitly save something to memory as an experience.

primeline-ai/evolving-lite · 9 tokens

evolution

Show what the system learned and changed recently.

primeline-ai/evolving-lite · 8 tokens

smartcompact

Pin important turns before compacting — pins survive compaction via SessionStart hook reinjection.

codeprakhar25/smartcompact · 17 tokens

recall

Search verbatim history from previous Claude Code sessions.

Reikor-Arg/inmemory · 9 tokens

reindex

Index the history of every project (one-time backfill).

Reikor-Arg/inmemory · 12 tokens

topics

Recurring themes distinctive to this project.

Reikor-Arg/inmemory · 6 tokens