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 tboome33/obsidian-mcp-router --skill write-frontmatter-mergegit clone --depth 1 https://github.com/tboome33/obsidian-mcp-routerWrote 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/tboome33/obsidian-mcp-router/write-frontmatter-merge)<a href="https://agentmods.dev/skills/tboome33/obsidian-mcp-router/write-frontmatter-merge"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/write-frontmatter-merge/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/tboome33/obsidian-mcp-router/write-frontmatter-merge"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/write-frontmatter-merge.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 | $0.00192 | $0.00890 |
| Opus 5 | $0.00096 | $0.00445 |
| Sonnet 5 | $0.00038 | $0.00178 |
| Haiku 4.5 | $0.00019 | $0.00089 |
Grade A, and why
write-frontmatter-merge 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 8d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
write-frontmatter-merge
Call the obsidian-router merge_frontmatter MCP tool with arguments parsed from $ARGUMENTS.
Arguments
Required:
path— file path relative to vault root.values— object map of keys/values to set.
Optional:
vault— omit for default.createIfMissing— create absent keys. Default true.ifMatch— acontentSha256from a priorget_file. Checked ONCE before any key is written; a mismatch throws a 409 before the first mutation. Guards against merging into a file that changed since you read it (it does not make the multi-key update atomic — see the warning below).
Argument parsing from $ARGUMENTS
path=X k1=v1 k2=v2 k3=v3— most natural formpath=X values={"k1":"v1","k2":"v2"}— JSON-explicit form- the user might phrase it conversationally: "marque le trade comme closed avec outcome=stopped" → infer values
Type inference per value
- numeric → number
true/false→ booleannull→ null[...]→ JSON array{...}→ JSON object- otherwise → string
⚠️ Not atomic on its own
Called directly, this is NOT atomic. If applying 5 updates and the 3rd fails, the first two are already applied. The tool returns a per-key status — surface that result honestly:
- N succeeded, M failed
- list the failed keys with their error
To make it all-or-nothing (v0.66.0+, borrowing C2): run it as a write_bundle step. The bundle captures the file's content before the first key is written, and treats a partial merge (failed > 0) as a failed step — so the file goes back to exactly what it was:
write_bundle({
vault, steps: [
{ op: "merge_frontmatter", path: "wiki/<page>.md", values: { status: "closed", outcome: "tp1" } }
]
})
Then read outcome: applied or rolled-back, never a half-updated file. This is the intended remedy — see the write-bundle skill. The older workaround (read the frontmatter, modify it client-side, write-create-or-replace the whole file) still works but rewrites the body too.
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.
- 8d ago First seen · 70 lines · 192 tokens per session scan A fb87e5b4b6ad
write-frontmatter-merge is a skill published in the GitHub repository tboome33/obsidian-mcp-router (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 192 tokens to every session and 890 once invoked, about $0.0010 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 2026-09-03.
Other skills, from other repositories
unanswered-messages
Scan WhatsApp + Gmail for messages still awaiting MY reply — the ones that need nothing more than an answer, so they spin off no case, reminder, or event and get forgotten — record each on the board as an unanswered message, and mark it answered the moment I reply (so it leaves the view). Use when the user says "what…
fitness-training-plan
The Fitness coach's HEADLINE skill — generate a personalised WEEKLY TRAINING PLAN for the athlete with deliberate VARIETY / ROTATION (rotate sports and intensity; alternate hard/easy; progressive overload toward the goal date), then PERSIST it via savetrainingplan so it lands on the /fitness/training-plan history…
usage-guard
Arm proactive 5-hour usage protection for long Claude Code sessions (batch, subagents, high window % at start). Daemon reads account-level 5-hour window usage (not per-session). User types /usage-guard at session start. Re-arm every sitting. If user mentions usage-guard by name, read this file and run arm.sh.
reminders-review
The reminder janitor — a periodic sweep that reviews every OPEN reminder on the board and CLOSES the ones whose job is already done or whose moment has passed, so the reminders list stays a live to-do surface instead of a graveyard of stale nudges. It reads each reminder's full context via the board MCP, then sorts it…
fitness-pre-workout-brief
Prepare and persist TODAY'S pre-workout / training-readiness brief — the daily "should I train today?" call. It reads the board's deterministic FORM SCORE (0–100, with its hrv / sleep / resting-HR / load breakdown), folds in last night's sleep + this morning's metrics + recent training load + the athlete profile +…
capture
Captures ideas, notes, links, and thoughts quickly. Use when the user says 'note', 'idea', 'capture', 'save this', 'remember', or wants to save something for later.