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.
git 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/arsave)<a href="https://agentmods.dev/commands/goldentrii/agentrecall-x/arsave"><img src="https://agentmods.dev/badge/commands/goldentrii/agentrecall-x/arsave.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 | $0.00016 | $0.03290 |
| Opus 5 | $0.00008 | $0.01645 |
| Sonnet 5 | $0.00003 | $0.00658 |
| Haiku 4.5 | $0.00002 | $0.00329 |
Grade C, and why
arsave scanned grade C 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 8d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- **Checkpoint saves allowed.** Multiple saves per day merge into one journal entry. Don't refuse a save just because one already happened today. How it starts
The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/arsave — AgentRecall Full Save
One command to save everything. No long prompts needed.
When to Use
Default: USE IT. Most projects are long-term. Memory compounds — insights saved today prevent repeated mistakes and rebuild costs across future sessions.
Skip /arsave only when the session was truly throwaway:
- Pure Q&A with no decisions made
- Trivial one-off task that won't be revisited
- Nothing non-obvious happened worth recalling
What This Does
Runs the complete AgentRecall end-of-session flow:
- Gather — review what happened this session
- Save — one
session_endcall writes journal + awareness + consolidation - Verify — check that key content was promoted
- Git — push to GitHub if user has configured it
Process
Step 1: Gather session context
Start with machine-captured facts, not memory. At long context windows your memory of early decisions is compressed and unreliable. Ground truth comes first:
-
Read today's capture log —
~/.agent-recall/projects/<slug>/journal/YYYY-MM-DD-log.md(if it exists). This file contains incremental Q&A captures logged during the session. Pull out the key facts from it. -
Check git diff — if in a git repo, run
git diff --stat HEADorgit log --oneline -5to see what files actually changed. -
Supplement with memory — now recall what happened that isn't in the log: decisions made in conversation, things we discussed but didn't act on, blockers identified, next steps.
Combine all three into a 2-3 sentence summary. The log anchors you; memory fills the gaps.
Step 1b: Capture intention on first save
Check whether this project already has an intention recorded:
grep -l "Intention:" ~/.agent-recall/projects/<slug>/palace/identity.md 2>/dev/null
If NOT found (this is the first save for this project, or intention was never captured):
Look at the earliest user messages in this conversation — where the user explained what they're trying to do, why they're starting this project, what problem they're solving, or what their goal is. Extract one clear sentence that captures the core WHY.
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.
- 8d ago First seen · 327 lines · 16 tokens per session scan C a614706b456f
arsave is a command published in the GitHub repository Goldentrii/AgentRecall-X (371 stars, last pushed 7d ago), licensed MIT. It adds 16 tokens to every session and 3,290 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). 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-provenance
Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.
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.
artel-remember
Write a fact, decision, or gotcha to Artel shared memory.
dream
Run a judgment session over the Pseudolife memory bank — triage the review queues; extract facts only where no extractor can.
artel-recall
Search Artel shared memory for what the fleet already knows.