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 blackmo18/realm --skill realm-recallgit clone --depth 1 https://github.com/blackmo18/realmWrote 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/blackmo18/realm/realm-recall)<a href="https://agentmods.dev/skills/blackmo18/realm/realm-recall"><img src="https://agentmods.dev/badge/skills/blackmo18/realm/realm-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/blackmo18/realm/realm-recall"><img src="https://agentmods.dev/badge/skills/blackmo18/realm/realm-recall.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 | $0.00131 | $0.02029 |
| Opus 5.5 | $0.00052 | $0.00812 |
| Sonnet 5.5 | $0.00026 | $0.00406 |
| Haiku 4.5 | $0.00013 | $0.00203 |
Grade A, and why
realm-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 1mo 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
realm-recall
Host invocation: Claude Code and Gemini use /realm-recall; Codex uses $realm-recall.
Ask vault anything. Get compressed context back. Optimized for ADR queries.
Syntax
/realm-recall <topic> # NL topic, decision keyword, tag
/realm-recall <topic> --trace # Link tree only (zero content, <10 tokens)
/realm-recall <topic> --full # Full prose for matched nodes
/realm-recall <topic> --deps # Include [[depends_on]] nodes (compressed)
/realm-recall <topic> --count # Estimate token cost before pulling
/realm-recall <topic> --expand <id> # Expand one node's full prose after compressed view
/realm-recall <topic> --no-canvas # Skip canvas expansion even if source_plan present
ADR Query Patterns
The primary reason to use realm-recall — answering questions code can't answer:
/realm-recall "why JWT"
→ decision nodes where JWT appears in title/context/rationale (~20 tokens)
/realm-recall "what was rejected for auth"
→ ADR nodes with non-empty rejected_alternatives field, #auth tag (~30 tokens)
/realm-recall "constraint on payments"
→ decision nodes with consequences field mentioning payments (~25 tokens)
/realm-recall "has anyone tried websockets"
→ searches rejected_alternatives across all ADRs for websocket mentions
/realm-recall decisions
→ all ADR nodes, compressed (~20 tokens each)
/realm-recall decisions --full
→ full prose for all ADRs including context, rejected, consequences
Canvas Lazy-Load (source_plan)
When an ADR was promoted from a realm-plan canvas, its source_plan field points to the
canvas dir. realm-recall intent-maps the query to exactly one canvas section and reads only
that file. Cost: ADR compressed (~20t) + one section (~80–150t). Suppress with --no-canvas.
Trigger-word table, resolution steps, and worked examples: references/canvas-expansion.md
(loads only in Step 4.5, only when a loaded node has source_plan).
General Query Examples
/realm-recall auth
→ All #auth nodes → compressed view
/realm-recall "session refresh"
→ Semantic → decision/discovery nodes matching phrase
/realm-recall auth --trace
→ Auth dependency tree, no content (<10 tokens) → explore in Obsidian
/realm-recall #critical-path --count
→ "12 nodes, ~240 tokens compressed, ~1800 tokens full"
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 213 lines · 131 tokens per session scan A 3097a6c1c97a
realm-recall is a skill published in the GitHub repository blackmo18/realm (0 stars, last pushed 2mo ago), licensed MIT. It adds 131 tokens to every session and 2,029 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, source notes, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…