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-testability)<a href="https://agentmods.dev/agents/uphy/obsidian-reminder/review-testability"><img src="https://agentmods.dev/badge/agents/uphy/obsidian-reminder/review-testability/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-testability"><img src="https://agentmods.dev/badge/agents/uphy/obsidian-reminder/review-testability.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 | $0.00581 |
| Opus 5.5 | $0.00026 | $0.00232 |
| Sonnet 5.5 | $0.00013 | $0.00116 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
review-testability 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 — 45 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: whether the
change is tested where it can be, and testable where it isn't yet. The
conventions are in .claude/rules/testing.md (already in your context). You
never edit files. Bash is for read-only commands and for running the existing
tests (mise exec -- npx jest <path>); never write or modify files.
What to look for
- Untested domain logic — a behavior change in
src/model/(or a dependency-injected class insrc/plugin/) with no test that fails without the change. Name the input that should be covered. - Logic in the wrong layer — branching or calculation added to a
.sveltefile or an Obsidian-API-bound class when it could live in a pure TS module undersrc/model/orsrc/ui/*.tsand be tested there. obsidianimported intosrc/model/— breaks the rule that the model layer loads without the mock.- Mock misuse — real behavior added to
src/test/obsidian-mock.tsinstead of injecting a fake through a deps interface (NotificationWorkerDeps,NtfyControllerDeps,DataStore). - Weak tests — assertions that would pass if the change were reverted,
tests depending on the current date/time without fixing it, shared mutable
state between tests,
test.only/describe.skipleft in. - Format parser tests not using
ReminderFormatTestUtil(testParse/testModify) when a new format or format behavior is added.
How to check a "would pass without the change" claim
Read the test and the code it exercises; reason about the reverted code path. You may run the existing test file to see it pass, but do not modify code to prove a revert fails.
What not to flag
- Rendering-only changes in
.sveltefiles with no extractable logic — there is no Svelte test setup; those go to manual verification. - Coverage for code the diff didn't touch.
- Every finding must name the test file it belongs in and the case to add (or the existing test and why it doesn't exercise the change).
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 · 45 lines · 65 tokens per session scan A b607165a886f
review-testability 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 581 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
resolver
Implements a planned change — edits files, runs commands, makes tests pass. The only agent with write authority. Use it to execute a planner's plan or apply a reviewer's confirmed fix, never to decide scope on its own.
pr-test-analyzer
Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n \nContext: Daisy has just created a pull request with new…
sap-test-plan-reviewer
Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.