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 skills add joshuaswarren/remnic --skill remnic-recallgit clone --depth 1 https://github.com/joshuaswarren/remnicWrote 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/skills/joshuaswarren/remnic/remnic-recall)<a href="https://agentmods.dev/skills/joshuaswarren/remnic/remnic-recall"><img src="https://agentmods.dev/badge/skills/joshuaswarren/remnic/remnic-recall/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/skills/joshuaswarren/remnic/remnic-recall"><img src="https://agentmods.dev/badge/skills/joshuaswarren/remnic/remnic-recall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.00488 |
| Opus 5 | $0.00017 | $0.00244 |
| Sonnet 5 | $0.00007 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
remnic-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 12d 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
When to use
Use when the user or the current task needs prior context from Remnic. This is the default first step for any non-trivial Claude Code turn that could benefit from memory.
Triggers:
- "What do you remember about …"
- "Have we talked about …"
/remnic:recall <query>slash command invocation.- A new task begins and the agent wants background.
Inputs
query(required) — natural-language question or topic string.- Optional: caller-supplied budget hint (brief, deep).
Procedure
- Build a concise natural-language query from the user's message. Prefer the user's own wording.
- Call
remnic_recallwith that query; request 3–8 results unless the caller specified otherwise. - Filter results for topical relevance.
- Present 1–5 bullet points summarizing the relevant memories, attributed when useful.
- If nothing relevant came back, say so plainly and suggest
remnic-rememberif there is something worth storing now.
Efficiency plan
- One broad recall beats several narrow ones.
- Reuse recall results within the same turn — do not re-query the same topic.
- Skip recall for trivially local tasks.
Pitfalls and fixes
- Pitfall: Quoting irrelevant recalls just because they came back. Fix: Filter for relevance before surfacing.
- Pitfall: Over-narrowing the query. Fix: Start broad; refine only when the first pass was noisy.
- Pitfall: Showing raw memory payloads. Fix: Summarize in the user's own terms.
Verification checklist
-
remnic_recallwas called with a natural-language query. - Results were filtered for relevance before being shown.
- Summary is ≤ 5 bullets unless the user asked for more.
- Canonical
remnic_recallwas used over legacyengram_recall.
Tool names: canonical name is
remnic_recall. The legacyengram_recallalias remains accepted during v1.x.
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.
- 12d ago First seen · 52 lines · 35 tokens per session scan A 892d1c78ce90
remnic-recall is a skill published in the GitHub repository joshuaswarren/remnic (198 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 488 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 skills, from other repositories
claude-memory
Access the persistent memory database (PostgreSQL claudememory) for long-term context across Claude Code sessions. Triggers on "what do I know about", "memory lookup", "recall", "memory db", "what did we decide about", "similar conversations", "lookup context", "/memory". Provides semantic search, SQL queries and the…
project-context-loader
Load relevant memory, decisions and contacts for the current project at the start of a session.
plur-create-engrams
Create or improve PLUR engrams from conversations, documents, decisions, observations, and explicit preferences. Use for memory extraction, engram authoring, or reviewing proposed memories, including global, scoped, pinned, retrieved, and provisional knowledge. Ordinary use of existing memories does not require this…
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
plur-session-end
Extract durable learnings at the end of a session. Saves corrections, preferences, and codebase patterns as engrams — nothing ephemeral, nothing sensitive.
plur-memory
Your memory stays on your machine. No cloud, no tracking, no API key. PLUR makes your OpenClaw remember — and shares that memory with every other tool you use.