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 meta-audit-bridge-readinessgit 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/meta-audit-bridge-readiness)<a href="https://agentmods.dev/skills/tboome33/obsidian-mcp-router/meta-audit-bridge-readiness"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/meta-audit-bridge-readiness/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/meta-audit-bridge-readiness"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/meta-audit-bridge-readiness.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 | $0.00000 | $0.01670 |
| Opus 5 | $0.00000 | $0.00835 |
| Sonnet 5 | $0.00000 | $0.00334 |
| Haiku 4.5 | $0.00000 | $0.00167 |
Grade A, and why
meta-audit-bridge-readiness 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
meta-audit-bridge-readiness
Diagnostic read-only de la fonctionnalité click-to-open (http://127.0.0.1:<port>/open/<path> qui ouvre un fichier dans Obsidian). C'est le complément de [[meta-status]] : meta-status vérifie que le router peut joindre chaque vault ; ce skill-là vérifie que les liens cliquables que tu mets dans le chat fonctionnent vraiment.
Quatre prérequis sont checkés par vault :
| # | Check | Si KO |
|---|---|---|
| 1 | mcp-router-bridge plugin ≥ v0.2.0 installé |
route handler /open/* absent → npm run deploy:all dans le bridge repo |
| 2 | obsidian-local-rest-api plugin ≥ v4.0.0 installé |
méthode addPublicRoute() absente → update via Settings Community Plugins, ou copy v4.x dans .template + --sync-all --force |
| 3 | enableInsecureServer: true + insecurePort set dans .obsidian/plugins/obsidian-local-rest-api/data.json |
serveur HTTP non-chiffré coupé → AV (Bitdefender etc.) va dropper les HTTPS auto-signés silencieusement |
| 4 | Live probe : GET http://127.0.0.1:<insecurePort>/open/__nonexistent__.md retourne 404 (= route enregistrée) plutôt que 401 (= middleware auth catch-all = route pas registered) |
Obsidian a du code stale en mémoire → Ctrl+P → "Reload app without saving" |
Le check #4 est le plus important — c'est lui qui détecte le cas où les fichiers sur disque sont corrects mais Obsidian tourne encore avec l'ancien code (n'a pas reload depuis le sync). Les checks 1-3 sont des static-version checks.
Steps
-
Run the audit script and capture its JSON output:
node "<router-repo>/scripts/meta-audit-bridge-readiness.mjs" --json(or for a single vault:
--vault <slug-or-path>) -
Parse the JSON. Schema:
{ "minBridge": "0.2.0", "minLra": "4.0.0", "results": [ { "vaultName": "DEDIBOX", "vaultPath": "C:\\VAULTS\\DEDIBOX", "httpsPort": 27131, "insecurePort": 27141, "bridgeVersion": "0.2.0", "lraVersion": "4.0.2", "enableInsecureServer": true, "checks": { "bridgeInstalled": true, "bridgeOk": true, "lraInstalled": true, "lraOk": true, "insecureEnabled": true, "routeLive": true, "probeResult": { "status": 404, "error": null } }, "ready": true } ], "summary": { "total": 10, "ready": 3, "notReady": 7 } }
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 · 99 lines · 0 tokens per session scan A fea6930bd27d
meta-audit-bridge-readiness is a skill published in the GitHub repository tboome33/obsidian-mcp-router (1 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,670 tokens. 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
test-master
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.
debugging-wizard
Use when investigating errors, analyzing stack traces, or finding root causes of unexpected behavior. Invoke for error investigation, troubleshooting, log analysis, root cause analysis.
spec-miner
Use when understanding legacy or undocumented systems, creating documentation for existing code, or extracting specifications from implementations. Invoke for legacy analysis, code archaeology, undocumented features.
librarian
Orchestrate vault knowledge workflows using the Librarian MCP server. Ingest solutions, search prior art, explore the knowledge graph, log daily learnings.
vault-lint
Obsidian vault health checker. Detects broken links, orphan pages, index.md inconsistencies, cross-reference gaps, and frontmatter validation. Inspired by Karpathy's LLM Wiki lint pattern. Triggers: "/vault-lint", "check vault", "vault health", "lint notes".
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.