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 manual-verifygit 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/manual-verify)<a href="https://agentmods.dev/skills/uphy/obsidian-reminder/manual-verify"><img src="https://agentmods.dev/badge/skills/uphy/obsidian-reminder/manual-verify/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/manual-verify"><img src="https://agentmods.dev/badge/skills/uphy/obsidian-reminder/manual-verify.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 | $0.00142 | $0.01330 |
| Opus 5 | $0.00071 | $0.00665 |
| Sonnet 5 | $0.00028 | $0.00266 |
| Haiku 4.5 | $0.00014 | $0.00133 |
Grade A, and why
manual-verify 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manual verification in a test vault
Automated tests only cover src/model/; anything touching the Obsidian API must be
verified by a human in a running Obsidian. This skill prepares everything so that the
user only has to launch Obsidian and walk through generated test notes.
Environment-specific configuration
Never hardcode vault paths, plugin directory names, or other machine-specific details
in this skill, in test notes' front matter, or in any committed file. Read them from
CLAUDE.local.md at the repository root (auto-loaded into context, gitignored).
Expected entries: test vault path, plugin symlink location, installed companion
plugins. If CLAUDE.local.md is missing or lacks the vault path, ask the user where
their test vault is and offer to record it in CLAUDE.local.md for next time.
Workflow
1. Build the code under verification
Run a production build in the checkout to verify (main repo or a worktree):
mise exec -- npm run build
Confirm the change is actually in the artifact before involving the user, e.g.
grep -c "<some string unique to the change>" main.js. The vault loads main.js,
manifest.json, and styles.css from the plugin directory; all three exist at the
checkout root after a build.
2. Point the vault at the checkout
ln -sfn <checkout-path> <vault>/.obsidian/plugins/<plugin-dir>
A git worktree works fine as the target: the hot-reload plugin watches any plugin
directory containing .git, and a worktree's .git file satisfies that.
3. Prepare plugin settings (the data.json gotcha)
Because of the symlink, the plugin's data.json lives at the checkout root (it is
gitignored). Two rules:
- Never edit
data.jsonwhile Obsidian is running. The live plugin periodically saves its in-memory state and will silently overwrite your edits. Stage the desired file in the session scratchpad, ask the user to quit Obsidian, copy it into place, verify the copy, then ask them to relaunch. - Set
"scanned": falseand"reminders": {}in the staged file. This forces a full vault rescan at startup; otherwise test notes created while Obsidian was closed may not be picked up (the plugin has no create-event listener, see #270).
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 · 123 lines · 142 tokens per session scan A 166e9f5eee30
manual-verify is a skill published in the GitHub repository uphy/obsidian-reminder (658 stars, last pushed 7d ago), licensed MIT. It adds 142 tokens to every session and 1,330 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.