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 thoreinstein/gemini-obsidian --skill vault-lintgit clone --depth 1 https://github.com/thoreinstein/gemini-obsidianWrote 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/thoreinstein/gemini-obsidian/vault-lint)<a href="https://agentmods.dev/skills/thoreinstein/gemini-obsidian/vault-lint"><img src="https://agentmods.dev/badge/skills/thoreinstein/gemini-obsidian/vault-lint/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/thoreinstein/gemini-obsidian/vault-lint"><img src="https://agentmods.dev/badge/skills/thoreinstein/gemini-obsidian/vault-lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.00939 |
| Opus 5.5 | $0.00026 | $0.00376 |
| Sonnet 5.5 | $0.00013 | $0.00188 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
vault-lint 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- vault-lint — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vault Lint
Comprehensive vault health audit. Checks five dimensions and presents a prioritized report with fix options.
Checks
1. Frontmatter Compliance
Scan Engineering/ notes for missing required frontmatter fields per VAULT_CONVENTIONS:
- Call
obsidian_list_noteswithsubfolder: "Engineering". - For each note, call
obsidian_read_noteand check frontmatter for:type:— must be pattern, trap, decision, or conceptproject:— must be presentstatus:— must be presenttags:— must be a listcreated:— must be a date
- Report notes with missing or malformed fields.
- Offer to fix with
obsidian_update_frontmatter(one at a time, user confirms).
2. Provenance Drift
Find Engineering/ notes where the provenance: block suggests high uncertainty:
- From the notes already read in Check 1, filter those with
provenance:frontmatter. - Flag notes where
inferred> 0.5 — these are majority-synthesized and may need source verification. - Flag notes where
ambiguous> 0.1 — these have unresolved contradictions. - Report flagged notes with their provenance fractions.
3. Stale Content
If .manifest.json exists at vault root:
- Read it with the
Readtool. - For each entry in
sources, check ifpages_createdorpages_updatednotes still exist usingobsidian_read_note. - If a source file's modification time on disk is newer than
ingested_at, the derived notes may be stale. - Report stale notes and suggest re-ingesting with
/wiki-ingest --force <source>.
If no .manifest.json exists, skip this check and note that no ingest tracking is available.
4. MOC Coverage
Check whether recent Engineering/ notes appear in at least one thematic MOC:
- Call
obsidian_list_noteswithsubfolder: "MOCs". - For each MOC, call
obsidian_read_noteand extract all[[wikilinks]]. - Build a set of all notes referenced by at least one MOC.
- Compare against the Engineering/ note list — any note not in the MOC set is uncovered.
- Exclude notes created in the last 24 hours (grace period).
- Report uncovered notes and suggest which MOC(s) they belong in via
obsidian_rag_query(query the note title against MOC titles).
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 · 103 lines · 65 tokens per session scan A f29e242bd85a
vault-lint is a skill published in the GitHub repository thoreinstein/gemini-obsidian (102 stars, last pushed 3d ago), licensed ISC. It adds 65 tokens to every session and 939 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
expert-librarian
An expert librarian that helps you organize, search, and synthesize your Readwise highlights and documents.
oma-doctor
Inspect native plugin readiness and deterministic workflow safety.
oma-hooks-validate
Validate native Antigravity hooks, capability boundaries, and workflow evidence.
oma-hooks
Inspect the three native guard events and their enforcement state.
oma-team-fix
Repair only the current Stop-scheduled batch of at most three issues.
oma-evidence
Read an Evidence Window from a real validator log without flooding context.