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/arrecall)<a href="https://agentmods.dev/commands/goldentrii/agentrecall-x/arrecall"><img src="https://agentmods.dev/badge/commands/goldentrii/agentrecall-x/arrecall/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/goldentrii/agentrecall-x/arrecall"><img src="https://agentmods.dev/badge/commands/goldentrii/agentrecall-x/arrecall.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00021 | $0.00728 |
| Opus 5 | $0.00010 | $0.00364 |
| Sonnet 5 | $0.00004 | $0.00146 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
arrecall 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/arrecall — Contextual Mid-Session Recall
On-demand search against AgentRecall's memory store. Use anytime during a session — not just at start or end.
Two Modes
Mode A: Explicit Query (/arrecall <query>)
Direct recall. Run immediately:
recall({ project: "<current-project>", query: "<query>" })
CLI equivalent if MCP tools aren't available: ar recall "<query>".
Show results. Done. Use when you know exactly what to ask for.
Mode B: Contextual Scan (/arrecall with no args)
The useful mode. Extract context from the current conversation and run targeted multi-query recall automatically.
- Read the last 10 messages of the current conversation
- Extract 3-5 keywords from topics being discussed (technical components, decisions, domain terms)
- Run parallel recall queries — one per most important keyword, plus one against the global/catchall project for cross-project awareness:
recall({ project: "<slug>", query: "keyword1" }) recall({ project: "<slug>", query: "keyword2" }) recall({ project: "<catchall-project>", query: "keyword1" }) - Merge and deduplicate results (same slug = same entry, skip duplicates)
- Show the compact hit list:
──────────────────────────────────────
ArRecall — contextual hits
──────────────────────────────────────
[palace/decisions] We chose X over Y because... (2026-04-12)
[awareness] API returns null when session expires (6× confirmed)
[correction] Never push without permission [P0]
──────────────────────────────────────
3 results for: proxy auth, 407 error, headers
- If 0 results: say "No hits for these topics — memory may not have captured this yet." and continue.
When to Invoke
Run /arrecall at these moments — don't wait to be asked:
- Before any technical implementation — query the component or domain you're about to touch
- Before making an architectural decision — query the decision topic
- When something seems familiar but details are fuzzy — trust the instinct, run the query
- When the user says "last time" or "before" — they're signaling that memory exists; go find it
- When you hit a weird error — check if it's been seen before
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.
- 9d ago First seen · 72 lines · 21 tokens per session scan A 14da49fc24fa
arrecall is a command published in the GitHub repository Goldentrii/AgentRecall-X (371 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 728 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 2026-08-30.
Other commands, from other repositories
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.
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).
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.
artel-remember
Write a fact, decision, or gotcha to Artel shared memory.