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.
npx agentmods add commands/lovelaceloom/grok-plugin-cc/memorygit clone --depth 1 https://github.com/LovelaceLoom/grok-plugin-ccWhat 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 | $0.00011 | $0.00241 |
| Opus 5 | $0.00005 | $0.00120 |
| Sonnet 5 | $0.00002 | $0.00048 |
| Haiku 4.5 | $0.00001 | $0.00024 |
Grade A, and why
memory 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 2d 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.
What it actually says
Wrap grok memory. Grok's cross-session memory accumulates lessons across
calls (when enabled). Sub-actions:
/grok:memoryor/grok:memory stats— usage stats/grok:memory edit— open the memory store in an editor/grok:memory clear— wipe (be careful — irreversible)/grok:memory enable//grok:memory disable— toggle for this workspace
Per-call kill-switches are also available as flags on every command:
--no-memory (disable for one call) or --experimental-memory (enable for
one call, when not globally on). They're mutually exclusive.
Raw user input:
$ARGUMENTS
Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" memory "$ARGUMENTS"
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.
- 2d ago First seen · 28 lines · 11 tokens per session scan A f2f66d969d44
memory is a command published in the GitHub repository LovelaceLoom/grok-plugin-cc (5 stars, last pushed 25d ago), licensed Apache-2.0. It adds 11 tokens to every session and 241 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 2026-08-31.
Other commands, from other repositories
test-tools
Test MCP NixOS Tools (project).
spec-audit
Review — attack the SPEC before any code is written.
spec
Think — write the lean SPEC that the build will be measured against.
implement
Do — execute the SPEC in a fresh context, validating each step.
project
Think — plan the work and write a lean SPEC before building.
qa
Dispatch a verifiable browser task to the qa-tester subagent. Use for regression checks, smoke tests, and any task with a clean pass/fail outcome. Supports an EXHAUSTIVE mode that verifies every control behind an honesty gate.