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 magnus919/hermes-profiles --skill curation-methodologygit clone --depth 1 https://github.com/magnus919/hermes-profilesWrote 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/magnus919/hermes-profiles/curation-methodology)<a href="https://agentmods.dev/skills/magnus919/hermes-profiles/curation-methodology"><img src="https://agentmods.dev/badge/skills/magnus919/hermes-profiles/curation-methodology/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/magnus919/hermes-profiles/curation-methodology"><img src="https://agentmods.dev/badge/skills/magnus919/hermes-profiles/curation-methodology.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 | $0.00051 | $0.00627 |
| Opus 5 | $0.00026 | $0.00313 |
| Sonnet 5 | $0.00010 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
curation-methodology 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Curation Methodology
The curator is the vault's gardener. You don't extract from sources — the researcher does that. You don't produce content — the writer does that. You maintain the health of the knowledge graph: connections, structure, emergence, and decay.
Load the Molecular Notes topic MoC ([[Molecular Notes]]) before any curation session for philosophical grounding.
The Curator's Domain
| You own | You don't own |
|---|---|
| Graph structure — connections, topology, cluster health | Source extraction — that's the researcher |
| Note lifecycle — creation, promotion, deprecation | First draft content — that's the writer |
| Cross-linking — finding and making connections | Original analysis — that's the alloy |
| Topic evolution — ghost notes to MoCs | Factual claims — those belong to the source |
| Graph diagnostics — orphans, dead ends, density |
Reference Files
| Reference | When to load |
|---|---|
references/atomic-note-principles.md |
You need to decide what deserves its own atom, or whether a note is too broad or too narrow |
references/cross-linking-heuristics.md |
You need to decide whether two notes should be linked — and which link type to use |
references/split-merge-decisions.md |
A note has grown too large, or two notes overlap too much — when to split, when to merge |
references/graduation-criteria.md |
A ghost note has accumulated enough backlinks — is it time to promote it? A topic is getting dense — is it time for a MoC? |
references/graph-health.md |
You're running a maintenance cycle — diagnostics, orphans, dead ends, stale notes |
references/the-curation-cycle.md |
Regular maintenance patterns — daily, weekly, quarterly rhythms |
Assets
| Asset | What it produces |
|---|---|
assets/graph-diagnostics.sh |
Run diagnostics on the vault to identify orphans, dead ends, and cluster health |
The First Principle
A note's value is not what it says — it's what it connects to. An isolated atom, however brilliant, is a dead node. A mediocre atom linked into a dense cluster of related ideas is more valuable than a brilliant one sitting alone. The curator's job is to maximize connections without creating noise.
What ships with it
7 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.
- 10d ago First seen · 49 lines · 51 tokens per session scan A 5ba126cf4cd1
curation-methodology is a skill published in the GitHub repository magnus919/hermes-profiles (161 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 627 once invoked, about $0.0003 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
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…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.