A command that turns automatic extraction of useful notes from past coding sessions on or off.

Use it to check the current setting or enable or disable session-memory extraction for a project or globally.

It lets you control whether previous session transcripts are converted into searchable memory records.

memory — Command by greppable

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/greppable/greppable-cc-plugin/memory

Clone the repo

git clone --depth 1 https://github.com/greppable/greppable-cc-plugin

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 716 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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	$0.00019	$0.00716
Opus 5	$0.00010	$0.00358
Sonnet 5	$0.00004	$0.00143
Haiku 4.5	$0.00002	$0.00072

Measured yesterday against content hash f4ea584ada78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

memory scanned grade B with 1 finding 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 yesterday.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

project_val=$(grep -m1 '^memory:' .claude/greppable.local.md 2>/dev/null | awk '{print $2}')

commands/memory.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/greppable:memory — Toggle Session Memory Extraction

Usage

/greppable:memory — show current status /greppable:memory on — enable memory extraction /greppable:memory off — disable memory extraction

Flow

Read current config — check .claude/greppable.local.md (project) and ~/.claude/greppable.local.md (global) for memory key. Use:

project_val=$(grep -m1 '^memory:' .claude/greppable.local.md 2>/dev/null | awk '{print $2}')
global_val=$(grep -m1 '^memory:' ~/.claude/greppable.local.md 2>/dev/null | awk '{print $2}')
val="${project_val:-$global_val}"
[[ "$val" == "true" ]] && echo "enabled" || echo "disabled"

If no argument (status only):
- Report: "Session memory extraction is currently enabled/disabled."
- If enabled, show where memories are written: <gdl_root>/memory/active/
- If disabled, explain: "Run /greppable:memory on to enable. When a new session starts, the previous session's transcript is processed into searchable .gdlm memory records."
If argument is on:
- Find the config file. Prefer project-scope (.claude/greppable.local.md). If only global exists, use that. If neither exists, tell user to run /greppable:onboard first.
- If memory: key exists and value is false, change memory: false → memory: true using Edit tool.
- If memory: key exists and value is already true, confirm: "Memory extraction is already enabled."
- If memory: key doesn't exist, add memory: true on a new line after discovery_auto_prompt: using Edit tool.
- Confirm: "Memory extraction enabled. When your next session starts, the previous session will be processed into .gdlm records. Restart Claude Code for changes to take effect."
If argument is off:
- Same config detection as on.
- If memory: key exists and value is true, change memory: true → memory: false using Edit tool.
- If memory: key exists and value is already false, confirm: "Memory extraction is already disabled."
- If memory: key doesn't exist, add memory: false on a new line after discovery_auto_prompt: using Edit tool.
- Confirm: "Memory extraction disabled. Session transcripts will no longer be processed. Restart Claude Code for changes to take effect."

Read the full file on GitHub · 52 lines

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.

yesterday First seen · 52 lines · 19 tokens per session scan B f4ea584ada78

Subscribe to this mod's changes

memory is a command published in the GitHub repository greppable/greppable-cc-plugin (3 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 716 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI Memory and context Research ai-agents claude-code claude-code-plugin code-search gdl grep

memory

Getting it into your agent

What it costs to keep this loaded

Grade B, and why

Reads agent configuration directoriesmediumAgent snooping

How it starts

/greppable:memory — Toggle Session Memory Extraction

Usage

Flow

What this file has done since we first saw it

Other commands, from other repositories

rb-ask

rb-refresh

rp-build-cli

call-graph

index

search