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 EnkrateiaLucca/skills --skill relate-notesgit clone --depth 1 https://github.com/EnkrateiaLucca/skillsWrote 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/enkrateialucca/skills/relate-notes)<a href="https://agentmods.dev/skills/enkrateialucca/skills/relate-notes"><img src="https://agentmods.dev/badge/skills/enkrateialucca/skills/relate-notes/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/enkrateialucca/skills/relate-notes"><img src="https://agentmods.dev/badge/skills/enkrateialucca/skills/relate-notes.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 | $0.00128 | $0.01638 |
| Opus 5 | $0.00064 | $0.00819 |
| Sonnet 5 | $0.00026 | $0.00328 |
| Haiku 4.5 | $0.00013 | $0.00164 |
Grade A, and why
relate-notes 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Relate Notes
Given a main note (usually an outline or bites file) and one or more source notes (notes with material to mine), find the bullets/paragraphs in the source(s) that genuinely support specific bullets in the main note. Add Obsidian block-anchors (^id) to those blocks in each source, then add linked-bullet references in the main note that point at those exact blocks.
The result is the institutional-memory move: the main note ends up standing on everything the vault already knows, with links like [[Meeting Notes - Expert Call - 2026-04-21#^47c6a0 | frankenstein skill]] that Cmd-click jumps straight to in Obsidian.
Configuration
| Setting | Env var | Default |
|---|---|---|
| Vault location | OBSIDIAN_VAULT_DIR |
~/notes |
Resolve in this order: explicit user instruction → environment variable → default. All note paths are relative to the vault unless an absolute path is given.
Inputs to extract from the user's request
- Main note — the outline/bites file that gets new bullets added (required, single file).
- Source(s) — can take three forms (required):
- A single note path (e.g.
Licklider - Man-Computer Symbiosis.md). - A comma- or newline-separated list of note paths.
- A search description instead of paths — e.g. "any note about agents and learning", "all my notes on context engineering". In this case, discover candidates yourself (see Discovery below).
- A single note path (e.g.
- Connection kind — what kind of relationships to look for (optional). Examples: "anything about scoping", "only the rubric/litmus-test angle". If absent, decide based on the topics in the main note.
- Count — total number of block links to produce across all sources (optional, default 3). Distribute across sources by signal strength, not evenly.
- Max sources — cap on how many distinct source notes to draw from when a search description is given (optional, default 5). Keeps the result reviewable.
If the main note is missing or ambiguous, ask the user. Don't guess paths — verify with ls if unsure.
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 · 84 lines · 128 tokens per session scan A 2f3cf3ce6689
relate-notes is a skill published in the GitHub repository EnkrateiaLucca/skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 128 tokens to every session and 1,638 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
comet-memory
A review step for deciding whether information should become durable personal memory. It can keep, update, forget, or skip memory candidates based on bounded evidence.
recall-memory
Recall relevant long-term memories on demand. Given a topic or question, judges relevance from pre-loaded metadata, loads only relevant files, and returns a concise summary to the main agent.
agent-expert-creation
Create specialized agent experts with pre-loaded domain knowledge using the Act-Learn-Reuse pattern. Use when building domain-specific agents that maintain mental models via expertise files and self-improve prompts.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
self-improve
Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past…