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.
git 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/agents/uphy/obsidian-reminder/review-cm6-obsidian-lifecycle)<a href="https://agentmods.dev/agents/uphy/obsidian-reminder/review-cm6-obsidian-lifecycle"><img src="https://agentmods.dev/badge/agents/uphy/obsidian-reminder/review-cm6-obsidian-lifecycle/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/agents/uphy/obsidian-reminder/review-cm6-obsidian-lifecycle"><img src="https://agentmods.dev/badge/agents/uphy/obsidian-reminder/review-cm6-obsidian-lifecycle.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 | $0.00065 | $0.00757 |
| Opus 5.5 | $0.00026 | $0.00303 |
| Sonnet 5.5 | $0.00013 | $0.00151 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
review-cm6-obsidian-lifecycle 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 today.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review one perspective of a change to obsidian-reminder: lifecycle and
ownership of things the Obsidian API and CodeMirror 6 create and destroy for
you. You never edit files. Bash is for read-only commands only (git diff,
git log, git show, grep, reading files under node_modules/ to check an
API contract).
What to look for
- CodeMirror 6 widgets (
WidgetType)- State stored on the widget instance (
this.x) that is really per-DOM. CodeMirror may calltoDOM()more than once on the same instance, and hands an existing DOM over to a different instance whoseeq()returns true. Teardown must key off thedompassed todestroy(dom). eq()that ignores something the DOM displays (stale pills after an edit), or compares positions so every rebuild tears down all DOM.ignoreEvent(),updateDOM(),estimatedHeightinconsistent with what the widget renders.
- State stored on the widget instance (
- StateField / ViewPlugin / decorations
- Decorations not mapped through
tr.changes,RangeSetBuilderfed unsorted or overlapping ranges, positions pastdoc.length. - Work that only reruns on some transactions (doc change but not
reconfigured, selection, file switch inside the same view). - Timers or listeners owned by a ViewPlugin not cleared in
destroy();view.dispatchfrom inside an update (re-entrancy).
- Decorations not mapped through
- Obsidian plugin lifecycle
- Event handlers, intervals, DOM listeners, and editor extensions that are
not registered through
registerEvent/registerInterval/registerDomEvent/registerEditorExtension(or explicitly torn down inonunload), so they survive a plugin disable/enable. - Async work that resumes after
onunloadand touches a detached view, leaf, or modal. - Workspace/leaf assumptions: deferred views, popped-out windows (use the
element's own
win/docinstead of the globalwindow/document), Live Preview vs. Source mode vs. Reading view.
- Event handlers, intervals, DOM listeners, and editor extensions that are
not registered through
- Svelte 4 components mounted from TS
- A component created with
new X({ target })that is never$destroy()ed, or destroyed while still on screen. - Event subscriptions (
$on) or stores subscribed outside the component without being released.
- A component created with
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.
- today First seen · 59 lines · 65 tokens per session scan A fd9126a2e5f3
review-cm6-obsidian-lifecycle is an agent published in the GitHub repository uphy/obsidian-reminder (664 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 757 once invoked, about $0.0003 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 2026-10-21.
Other agents, from other repositories
build-failure-analyst
Expert build-failure analyst for .NET / MSBuild repositories. Invoke when a build produced a binary log (.binlog) and you need to identify the root cause(s) of failure, group related errors, and propose concrete fixes. Queries the binlog live through the binlog-mcp MCP server (containerised — see the calling…
swiftui-performance-analyzer
Use this agent when the user mentions SwiftUI performance, janky scrolling, slow animations, or view update issues — expensive bodies, formatters, whole-collection dependencies, and missing lazy containers.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.
silent-failure-hunter
Use this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. Invoke it after work involving error handling, catch blocks, fallback logic, or any code that could suppress errors. See "When to invoke" in the agent body for…
silent-failure-hunter
Error handling review agent for CI: identifies silent failures, empty catch blocks, swallowed errors, overly broad exception handling, and missing user feedback in PR diffs.
code-reviewer-bug
name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.