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 GregoryHo/arcforge --skill maintaining-obsidiangit clone --depth 1 https://github.com/GregoryHo/arcforgeWrote 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/gregoryho/arcforge/maintaining-obsidian)<a href="https://agentmods.dev/skills/gregoryho/arcforge/maintaining-obsidian"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/maintaining-obsidian/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/gregoryho/arcforge/maintaining-obsidian"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/maintaining-obsidian.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 | $0.00058 | $0.01924 |
| Opus 5.5 | $0.00023 | $0.00770 |
| Sonnet 5.5 | $0.00012 | $0.00385 |
| Haiku 4.5 | $0.00006 | $0.00192 |
Grade A, and why
maintaining-obsidian 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 today.
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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintaining Obsidian
Different vaults serve different domains — a second brain, a news pipeline, a
project tracker, a journal. This skill stays domain-agnostic and each vault
declares its own domain in a paired contract: AGENTS.md (runtime contract) and
SCHEMA.md (types, thresholds, taxonomy, language policy). The vault contract
wins wherever it overlaps this skill. The skill owns the mechanism: vault
resolution, the three pipelines, and the mechanical primitives.
Modes
| The user wants to | Mode | Pipeline |
|---|---|---|
| Save, capture, file back, ingest a source | ingest | Classify → Confirm → Create → Visuals → Index → Propagate → Log |
| Know what the vault already says | query | Orient → Search → Read → Synthesize → (File Back) |
| Check vault health | audit | LINK → LINT → GROW |
| Set up a vault that does not exist yet | init-vault | references/bootstrap-workflow.md |
No mode named and no clear intent: orient, do not ask "which mode?". Resolve the vault, read its contract, and answer with what this vault is — name, scope, declared types, last log entry — then ask what to do. Ask "ingest, query, or audit?" only when intent words are present but ambiguous.
Step 1 — Resolve the vault
Cascade, stopping at the first hit: explicit --vault=<name> → the vault
Obsidian currently has open (obsidian-cli vault, matched against the registry)
→ the vault already chosen earlier this session → the registry default → ask.
Print Operating on: <name> for every step below the first so a wrong guess can
be aborted. The choice is sticky for the session unless --vault overrides it.
Obsidian not running: skip to the session/default/ask steps and warn once that LINK resolution and live search degrade. Filesystem read and write still work.
Registry empty and the mode would write: stop, and offer init-vault or
arcforge obsidian register — never fall through to ad-hoc writes outside a
registered vault. A read-only query against a vault path the user has named
proceeds without registration; registering is not a toll gate on reading.
What ships with it
21 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.
- presets/llm-wiki/AGENTS.md 5.1 KB
- presets/llm-wiki/SCHEMA.md 14 KB
- presets/minimal/AGENTS.md 3.4 KB
- presets/minimal/SCHEMA.md 4.1 KB
- presets/news/AGENTS.md 4.7 KB
- presets/news/SCHEMA.md 8.8 KB
- presets/project-tracker/AGENTS.md 4.5 KB
- presets/project-tracker/SCHEMA.md 10 KB
- presets/README.md 2.1 KB
- references/audit.md 13 KB
- references/bootstrap-workflow.md 7.1 KB
- references/delegation.md 1.9 KB
- references/domain-contract-orientation.md 2.5 KB
- references/lint_vault.py 24 KB runs code
- references/mode-ingest.md 4.2 KB
- references/obsidian-cli-quirks.md 1.8 KB
- references/raw-sources.md 5.6 KB
- references/search-strategies.md 7.3 KB
- references/vault_frontmatter.py 21 KB runs code
- references/vault_links.py 8.6 KB runs code
- references/visuals-decision-tree.md 2.0 KB
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.
- today First seen · 139 lines · 58 tokens per session scan A ded195ab2079
maintaining-obsidian is a skill published in the GitHub repository GregoryHo/arcforge (8 stars, last pushed 12d ago), licensed MIT. It adds 58 tokens to every session and 1,924 once invoked, about $0.0002 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 2026-11-07.
maintaining-obsidian compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| maintaining-obsidianGregoryHo/arcforge | Skill | 8 | 12d ago | MIT | A | 58 | Claude Code |
| Migratedanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 104 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| Profiledanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 108 | Claude Code, Codex |
| wiki-dashboardAr9av/obsidian-wiki | Skill | 3.7k | yesterday | MIT | A | 42 | Claude Code |
| relevance-coarse-filterelvisun/newsjack | Skill | 1.7k | yesterday | MIT | A | 57 | Claude Code |
| session-compactcodeaholicguy/ai-devkit | Skill | 1.7k | 2d ago | Apache-2.0 | A | 39 | Claude Code |