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/goldentrii/agentrecall-x/arstartgit clone --depth 1 https://github.com/Goldentrii/AgentRecall-XWrote 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.
[](https://agentmods.dev/commands/goldentrii/agentrecall-x/arstart)<a href="https://agentmods.dev/commands/goldentrii/agentrecall-x/arstart"><img src="https://agentmods.dev/badge/commands/goldentrii/agentrecall-x/arstart.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00027 | $0.04290 |
| Opus 5 | $0.00014 | $0.02145 |
| Sonnet 5 | $0.00005 | $0.00858 |
| Haiku 4.5 | $0.00003 | $0.00429 |
Grade D, and why
arstart scanned grade D with 3 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 6d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- **Don't lecture.** Show the card, offer insights, then get out of the way. Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/projects/<your-user-dir>/memory/MEMORY.md Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
On second `d<N>`: run `rm -rf ~/.agent-recall/projects/<slug>/` and say "Deleted <slug>." How it starts
The opening of the file, as written. The whole thing — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/arstart — AgentRecall Session Opener
One command, three modes — the single entry point for every AgentRecall session.
| Invocation | Mode | Use when |
|---|---|---|
/arstart (no args) |
Board | You don't know what to work on yet — see everything in flight |
/arstart <slug> |
Load | You already know the project — load its full context |
/arstart bootstrap |
Bootstrap | First install, or backfilling projects AgentRecall doesn't know about yet |
USE THIS FIRST. Every new session — before any work, before picking up a task.
Mode: Board (no arguments)
The true cold start. One command to see everything in flight across all projects — for both humans choosing what to work on and agents loading briefing context.
When to Use
USE THIS FIRST. Every new session — before any work.
- Opening a new Claude Code tab or starting a fresh agent
- "What was I working on?" after any break
- Orchestrator loading full briefing before dispatching executor agents
- Deciding which project to pick up next
Board mode only tells you what to pick. Once you know the project, switch to Load mode (/arstart <slug>).
What This Does
Scans every project in ~/.agent-recall/projects/, reads the latest journal's ## Next section per project, classifies status, and renders a unified status board card.
Process
Step 1: Scan all project directories
ls ~/.agent-recall/projects/
For each subdirectory (project slug), find the latest journal file:
ls ~/.agent-recall/projects/<slug>/journal/*.md 2>/dev/null \
| grep -v '\-log\.' \
| grep -v 'index\.md' \
| sort -r \
| head -1
Skip any slug that returns no journal files — it's an empty or test directory.
Step 2: Extract date, Next section, and Intention
From each journal filename, extract the date (YYYY-MM-DD prefix).
Read the file and extract the content under ## Next — stop at the next ## heading or EOF. If no ## Next section exists, use the first non-frontmatter line of the file as fallback.
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.
- 6d ago First seen · 461 lines · 27 tokens per session scan D 69fb79b88a2e
arstart is a command published in the GitHub repository Goldentrii/AgentRecall-X (371 stars, last pushed 5d ago), licensed MIT. It adds 27 tokens to every session and 4,290 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 3 findings (strips warnings and disclaimers, reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
evolve-lite-retention
Apply data-retention rules to the local evolve store — flag or delete stale and unused memories and expired sessions (dry-run by default).
evolve-lite-adapt-memory
Mirror a just-saved native memory into the shared evolve store so it becomes shareable and auditable.
evolve-lite-provenance
Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.
artel-recall
Search Artel shared memory for what the fleet already knows.
artel-remember
Write a fact, decision, or gotcha to Artel shared memory.
memory-status
Check the Pseudolife-MCP memory daemon and report bank health.