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 cyanheads/obsidian-mcp-server --skill field-testgit clone --depth 1 https://github.com/cyanheads/obsidian-mcp-serverWrote 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/cyanheads/obsidian-mcp-server/field-test)<a href="https://agentmods.dev/skills/cyanheads/obsidian-mcp-server/field-test"><img src="https://agentmods.dev/badge/skills/cyanheads/obsidian-mcp-server/field-test/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/cyanheads/obsidian-mcp-server/field-test"><img src="https://agentmods.dev/badge/skills/cyanheads/obsidian-mcp-server/field-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 218 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Tool Misuse · line 330 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Data Exfiltration · line 109 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 125 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 151 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00106 | $0.11573 |
| Opus 5.5 | $0.00042 | $0.04629 |
| Sonnet 5.5 | $0.00021 | $0.02315 |
| Haiku 4.5 | $0.00011 | $0.01157 |
Grade D, and why
field-test scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
stats=$(curl -sS -o "$resp_file" -w '%{http_code} %{time_total}' -X POST "$url" "${headers[@]}" -d "$body") Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/<project-name>-field-test-<ID>-apps Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, measures every call (bytes, token estimate, wall-cl Copies of this mod
8 near-identical copies found in the catalogue:
- field-test — 100% identical, 5 lines differ
- field-test — 100% identical, 5 lines differ
- field-test — 100% identical, 0 lines differ
- field-test — 100% identical, 0 lines differ
- field-test — 100% identical, 0 lines differ
- field-test — 100% identical, 5 lines differ
- field-test — 100% identical, 0 lines differ
- field-test — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 565 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
Unit tests (add-test skill) verify handler logic with mocked context. Field testing exercises the real HTTP transport with real JSON-RPC: starts the server, calls initialize, surfaces the catalog, runs inputs, and checks what a client actually sees. It catches what unit tests miss — awkward input shapes, unhelpful errors, missing format output, drift between structuredContent and content[], edge-case surprises.
Actively call the tools. Don't read code and guess.
Transport coverage
This skill drives an HTTP server because curl + JSON-RPC is the most reliable harness for shell-based agents. The same handlers run on both transports — only the framing differs — so HTTP exercises the full functional surface. Both HTTP session modes are covered: a durable Mcp-Session-Id session, and the sessionless initialization a MCP_SESSION_MODE=stateless server performs.
Stdio coverage is a boot check only — run this before Step 1. Run bun run rebuild && bun run start:stdio < /dev/null, and confirm the startup logs look clean: the Core services constructed — N tool(s) … record lists every registered tool, resource, and prompt in its tools / resources / prompts fields — the message text shows only counts — and a definition missing from them was never passed to createApp(). No errors/warnings, no missing-config gripes. The emoji startup banner prints only to a terminal, so its absence from an agent's shell is not a finding. Redirecting stdin is what ends the run: the server treats EOF as a shutdown signal, boots fully, then exits on its own, so the log also shows the graceful-shutdown path. Do not background it and reach for pkill — a pattern like pkill -f dist/index.js matches every other stdio MCP server on the machine, including the ones the calling agent's own session is connected to. Pino logs go to stderr in stdio mode (stdout is reserved for JSON-RPC), so they print straight to the terminal when you run interactively. No need to call tools over stdio — the HTTP pass already covered handler behavior.
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.
- yesterday Changed · +1 lines e6f400f2b01d
- 20d ago Changed · +45 lines · +13 tokens per session scan B → D 9829199245e8
- 1mo ago Changed · +2 lines 62fbc6e452c2
- 1mo ago Changed · +5 lines 88d22478cafc
- 1mo ago Changed · +119 lines · +17 tokens per session scan A → B 370664dc34d6
- 1mo ago First seen · 393 lines · 76 tokens per session scan A 5e0878fedc2a
field-test is a skill published in the GitHub repository cyanheads/obsidian-mcp-server (701 stars, last pushed yesterday), licensed Apache-2.0. It adds 106 tokens to every session and 11,573 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it D with 3 findings (sends data to an external url, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
impl-validator
Independently check whether an implementation matches its stated goal and return PASS/WARN/FAIL with actionable issues. Use for second-opinion validation of an implementation or generated output.
api-test-suite-builder
Generate API tests from routes and contracts for authentication, validation, pagination, errors, uploads, and limits in Node.js or Python projects.
widget-authoring
Author or edit ThinkEx widgets, which are self-contained interactive HTML blocks inside documents. Use when the user explicitly asks for a widget, asks for interaction or live computation, or wants a document visual that ordinary blocks cannot express.
web-mocks-msw
MSW handlers, browser/server workers, test data. Use when setting up API mocking for development or testing, creating mock handlers with variants, or sharing mocks between browser and Node environments.
pkm-write
Use when writing to the vault — creating new notes (vaultwrite), editing existing notes (vaultedit, vaultappend, vaultupdatefrontmatter). Handles duplicate checking, link discovery, annotations, and index updates for new notes. Provides guidelines for modifications.
pkm-session-end
Use when wrapping up a work session — creates devlog entry, captures undocumented decisions/research/debugging, audits link health of session work, and updates project index. Primarily used via the pkm-capture agent.