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 uphy/obsidian-reminder --skill obsidian-e2egit clone --depth 1 https://github.com/uphy/obsidian-reminderWrote 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/uphy/obsidian-reminder/obsidian-e2e)<a href="https://agentmods.dev/skills/uphy/obsidian-reminder/obsidian-e2e"><img src="https://agentmods.dev/badge/skills/uphy/obsidian-reminder/obsidian-e2e/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/uphy/obsidian-reminder/obsidian-e2e"><img src="https://agentmods.dev/badge/skills/uphy/obsidian-reminder/obsidian-e2e.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 75 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00140 | $0.06733 |
| Opus 5.5 | $0.00056 | $0.02693 |
| Sonnet 5.5 | $0.00028 | $0.01347 |
| Haiku 4.5 | $0.00014 | $0.00673 |
Grade A, and why
obsidian-e2e 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.
How it starts
The opening of the file, as written. The whole thing — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.
obsidian-e2e: automated testing against a live Obsidian
Relationship to manual-verify
manual-verify prepares a test vault (symlink, settings, fixture notes) and then
hands the user a checklist to click through by hand. This skill instead drives that
same running Obsidian over CDP so an agent can fire reminders, click UI, and read
back internal state without a human in the loop.
They are complementary, not interchangeable:
- Things this skill can verify automatically: reminder firing timing, toast
contents, button clicks and their effect on the file, settings state,
Reminders/ReminderNotifierinternal state. - Things only a human can verify (see "What cannot be automated" below): the look and feel of macOS system notifications, whether a system notification click actually does the right thing, and anything that depends on the user's macOS notification style settings (Banners vs. Alerts, etc).
For anything touching src/plugin/ or src/ui/, prefer running both: this skill
for the parts it can check unattended, manual-verify for the rest.
The absolute safety requirement
This machine typically has several vaults registered and multiple open at once. Only a vault explicitly and physically marked as safe for testing (see "The actual guard" below) may ever be touched. Every other vault — personal or work — must never be written to, and, per the incident below, not even read.
The wrong-vault write incident (read this before changing any guard)
Earlier in this skill's development, a guard was verified by actually calling
app.vault.adapter.write(...) with OBSIDIAN_TEST_VAULT_NAME pointed at a real,
non-test vault, on the reasoning that "the guard should reject this." It did
not. The guard at the time only checked that the vault name in the CDP page
title was unambiguous and matched what the in-page code re-read from
app.vault.getName() — and a real vault's actual name is, by definition, a
perfectly real, unambiguous, matching vault name. The write silently succeeded,
creating a stray file in a real personal vault, which then had to be cleaned up.
What ships with it
8 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.
- scripts/lib/cdp-pages.mjs 1.4 KB runs code
- scripts/lib/vault-window.mjs 5.0 KB runs code
- scripts/obsidian-eval.mjs 9.7 KB runs code
- scripts/obsidian-launch.sh 7.2 KB runs code
- scripts/obsidian-shot.sh 5.8 KB runs code
- scripts/obsidian-wait.sh 2.6 KB runs code
- scripts/reminder-fire-rewrite.mjs 2.6 KB runs code
- scripts/reminder-fire.sh 4.2 KB runs code
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 · 499 lines · 140 tokens per session scan A 278cc906daea
obsidian-e2e is a skill published in the GitHub repository uphy/obsidian-reminder (664 stars, last pushed 11d ago), licensed MIT. It adds 140 tokens to every session and 6,733 once invoked, about $0.0006 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
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.