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/d2a8k3u/claude-code-memory/memory-recallgit clone --depth 1 https://github.com/d2a8k3u/claude-code-memoryWhat 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 | $0.00016 | $0.00189 |
| Opus 5 | $0.00008 | $0.00095 |
| Sonnet 5 | $0.00003 | $0.00038 |
| Haiku 4.5 | $0.00002 | $0.00019 |
Grade A, and why
memory-recall scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run this Bash and relay the result to the user. It toggles the per-project recall kill-switch: when set to off, the SessionStart, UserPromptSubmit, PreToolUse, and error-context hooks inject nothing, while auto-save (session-end) and the MCP memory tools keep working. normal re-enables recall; status (the default) just reports the current mode.
node "${CLAUDE_PLUGIN_ROOT}/server/dist/cli.js" recall-mode $ARGUMENTS
Then tell the user the mode now in effect. If they switched it off, remind them recall is silenced for this project only and that memories are still being saved; they can run /memory-recall normal to turn it back on.
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 · 13 lines · 16 tokens per session scan A 231474f9aee7
memory-recall is a command published in the GitHub repository d2a8k3u/claude-code-memory (7 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 189 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
release
You are performing a release for the mindkeg-mcp project. The user will provide the version as $ARGUMENTS (e.g., "0.2.0" or "patch" or "minor" or "major").
validate
Validate memory system hooks, capture pipeline, and recall functionality.
audit-log
View the secrets filtering audit log.
sync
Synchronize the memory index with git notes (local or remote).
capture
Capture a memory (decision, learning, blocker, progress, etc.) to the git-backed memory system.
scan-secrets
Scan existing memories for secrets and optionally remediate.