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/joseairosa/recall/loopgit clone --depth 1 https://github.com/joseairosa/recallWhat 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 | $0.00036 | $0.00443 |
| Opus 5 | $0.00018 | $0.00221 |
| Sonnet 5 | $0.00007 | $0.00089 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
recall-loop 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
/recall-loop
Run a periodic digest of your Recall memory. Shows what was stored recently and any pending to-dos. Designed to be scheduled with /loop.
Usage
/recall-loop # Digest of last 60 minutes (default)
/recall-loop 30 # Digest of last 30 minutes
/recall-loop 120 # Digest of last 2 hours
Scheduling with /loop
/loop 30m /recall-loop # Check in every 30 minutes
/loop 1h /recall-loop # Hourly digest
/loop 2h /recall-loop 120 # Every 2 hours, look back 2 hours
What it shows
- Recent memories — decisions, patterns, insights stored in the window
- Pending to-dos — overdue and high-priority items that need attention
Behavior
- Parse the optional
window_minutesargument (default: 60) - Call
mcp__recall-remote__loop_digestwith{ window_minutes, include_todos: true } - Present the formatted digest
- If overdue to-dos exist, surface them prominently
Example output
Recall Digest — Last 60m [14:30:00]
==================================================
MEMORIES 3 new
[decision] Chose Redis for session caching with 30-minute TTL
[insight] Auth middleware reads tenant context from req.tenant
[code_pattern] Always use generateUlid() for new IDs
TO-DOS
[OVERDUE] Review security audit report (high)
Write tests for billing service (medium)
--------------------------------------------------
Tip: /loop 60m /recall-loop
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 · 58 lines · 36 tokens per session scan A 9b0813ba87c7
recall-loop is a command published in the GitHub repository joseairosa/recall (175 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 443 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 2026-08-30.
Other commands, from other repositories
debug
Systematic debugging with hypotheses and evidence gathering.
context-stats
Show context window usage, active tier, and system stats.
think
Apply structured thinking frameworks to a problem.
whats-next
Show current project status and suggest next steps.
recover
Scan orphaned worktrees and stale branches, then offer explicit approval-gated cleanup.
capture
Triage raw inbox notes into reviewed repository destinations without deleting their sources.