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 tuan3w/obsidian-vault-agent --skill recallgit clone --depth 1 https://github.com/tuan3w/obsidian-vault-agentWrote 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/tuan3w/obsidian-vault-agent/recall)<a href="https://agentmods.dev/skills/tuan3w/obsidian-vault-agent/recall"><img src="https://agentmods.dev/badge/skills/tuan3w/obsidian-vault-agent/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/tuan3w/obsidian-vault-agent/recall"><img src="https://agentmods.dev/badge/skills/tuan3w/obsidian-vault-agent/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 | $0.00088 | $0.02480 |
| Opus 5 | $0.00044 | $0.01240 |
| Sonnet 5 | $0.00018 | $0.00496 |
| Haiku 4.5 | $0.00009 | $0.00248 |
Grade A, and why
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 10d 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Use_When>
- User wants a review session ("what should I review?", "quiz me", "recall practice")
- User wants to resurface notes they haven't seen in a while
- User wants to triage their inbox
- User wants to discover connections across domains
- User asks "what do I remember about X?"
- Periodic knowledge maintenance (daily, weekly reviews) </Use_When>
<Do_Not_Use_When>
- User wants to deeply process a specific note (use /process)
- User wants vault structure analysis (use /vault-graph)
- User wants to synthesize across a cluster (use /synthesize)
- User is actively reading or adding a new source note </Do_Not_Use_When>
<Execution_Policy>
- INTERACTIVE — never skip ahead. Each card requires the user to respond before the answer is shown. The friction IS the learning.
- Never show note content before the user attempts recall
- Prefer notes with updated_date older than 14 days (spacing effect)
- MUST interleave domains — draw from at least 3 different topic folders
- Use MCP tools (search_notes, get_frontmatter) when available; fall back to Grep/Glob
- Session size: default 5 retrieval cards, 2 inbox items, 1 surprise connection (adjust to user's argument if provided)
- After each reveal, offer to update the note if it's stale </Execution_Policy>
Stage 1: BUILD THE QUEUE
1a. Retrieval Practice Cards (default 3–5)
Candidate selection using MCP:
search_notes(query="processing_status: processed OR processing_status: evergreen", limit=50)
search_notes(query="type: term OR type: note", limit=50)
Or fall back to Grep:
Grep(pattern="processing_status: (processed|evergreen)", path="notes/", glob="*.md")
Grep(pattern="^type: (term|note)$", path="notes/", glob="*.md")
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.
- 10d ago First seen · 287 lines · 88 tokens per session scan A 87e1966d77bd
recall is a skill published in the GitHub repository tuan3w/obsidian-vault-agent (39 stars, last pushed 5mo ago), licensed MIT. It adds 88 tokens to every session and 2,480 once invoked, about $0.0004 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
documentation-writer
Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by the principles and structure of the Diátaxis technical documentation authoring framework. Templates for tutorial / how-to / reference / explanation live under templates/.
math-help
Guide to the math cognitive stack - what tools exist and when to use each.
math
Unified math capabilities - computation, solving, and explanation. I route to the right tool.
groups
Problem-solving strategies for groups in abstract algebra.
rings
Problem-solving strategies for rings in abstract algebra.
analytic-functions
Problem-solving strategies for analytic functions in complex analysis.