agentmods.dev

cm-share

cm-share is a command for Claude Code from Zenetusken/consolidate-memory. It costs 33 tokens per session (684 once invoked), scanned A, original, MIT.

A command for adding one verified fact to a shared memory store used across projects. It checks the claim against live repository files, shows the proposed change, and writes it only after user confirmation.

In plain words
What is it for?
Use it to author a cross-project fact, check whether it already exists, review the proposed addition or replacement, and save it after approval.
Why use it?
It prevents unverified, local, or duplicate information from becoming shared guidance. The verification and review step helps keep shared project knowledge accurate.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

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 +1 today A scan 33 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-share
Clone the repo
git clone --depth 1 https://github.com/Zenetusken/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.

agentmods badge for cm-share

README.md
[![agentmods](https://agentmods.dev/badge/commands/zenetusken/consolidate-memory/cm-share.svg)](https://agentmods.dev/commands/zenetusken/consolidate-memory/cm-share)
Your own site
<a href="https://agentmods.dev/commands/zenetusken/consolidate-memory/cm-share"><img src="https://agentmods.dev/badge/commands/zenetusken/consolidate-memory/cm-share.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 684 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 5.1 $0.00033 $0.00684
Opus 5 $0.00016 $0.00342
Sonnet 5 $0.00007 $0.00137
Haiku 4.5 $0.00003 $0.00068

Measured today against content hash a2269f80217d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

cm-share 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-share.md · 53 lines

What it actually says

A single fact into the shared layer, with the dream's own verification discipline (see docs/cm-commands-onboarding.spec.md §2.2). This is AUTHORING — the claim must survive verification before it may exist. NO VERIFY, NO WRITE.

  1. Read the single sources first (never paraphrase them): ${CLAUDE_PLUGIN_ROOT}/skills/consolidate-memory/references/harness-map.md § "verification recipes", and the Phase-2 scope cascade in ${CLAUDE_PLUGIN_ROOT}/skills/consolidate-memory/SKILL.md.

  2. Verify. Check the claim against THIS repo's live files/git with the recipes; for a user-global/stack-general scope, name at least one other existing project where it holds (G2.3). A claim that fails verification is reported and dropped, never written.

  3. Scope by content (the cascade, never vibes). A project-local claim does not belong here — point at cm local upsert instead.

  4. Dedup. Grep the domain canonicals for the same content; a duplicate reconciles onto the existing fact, never a second copy.

  5. Draft + show. Draft the fact (frontmatter + body) and SHOW it — including the before/after diff when the stem already exists (a replace freezes other projects' mirrors at their next pull). The user's confirmation is the gate. Groups (v0.4.10): when groups exist, ASK "share to a group or the whole domain?", and print the narrowing VERBATIM when a group is chosen — "delivery LIMITED to N members across X, Y; M same-domain projects STOP receiving it" — recipients narrow, never widen, and the exclusion is stated, never implied.

  6. Write through the sole canonical writer — one journaled transact (canonical + catalog + registry + this project's mirror + pointer):

    python3 "${CLAUDE_PLUGIN_ROOT}/scripts/cm_ops.py canonical upsert <stem> --file <draft-file> --origin --project .

    If the writer refuses with "recipients predate the current group — re-confirm (--repoint) or re-point": the draft's recipients: cite a group RECREATED after the draft's content_modified — the group's identity is fresh and the citation is stale. When the user confirms the narrowing against the CURRENT group (step 5's confirmation IS the re-confirmation), re-run with --repoint appended — the writer re-stamps the fact to now and accepts. Never hand-bump content_modified.

Enrolled projects only (the writer refuses otherwise). A secret-shaped draft is refused by the firewall — rephrase, never weaken it. A stack-general fact's stacks: must be detectable; the writer's own error names the undetectable set.

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 · 53 lines · 33 tokens per session scan A a2269f80217d

Subscribe to this mod's changes

cm-share is a command published in the GitHub repository Zenetusken/consolidate-memory (6 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 684 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.

Memory 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