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 divinevideo/divine-mobile --skill tests-guard-intentional-workaroundsgit clone --depth 1 https://github.com/divinevideo/divine-mobileWrote 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/divinevideo/divine-mobile/tests-guard-intentional-workarounds)<a href="https://agentmods.dev/skills/divinevideo/divine-mobile/tests-guard-intentional-workarounds"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/tests-guard-intentional-workarounds/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/divinevideo/divine-mobile/tests-guard-intentional-workarounds"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/tests-guard-intentional-workarounds.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 | $0.00240 | $0.02159 |
| Opus 5.5 | $0.00096 | $0.00864 |
| Sonnet 5.5 | $0.00048 | $0.00432 |
| Haiku 4.5 | $0.00024 | $0.00216 |
Grade A, and why
tests-guard-intentional-workarounds 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tests Guard Intentional Workarounds
Problem
You observe a production log line that looks clearly wrong — a function being called when its precondition already appears satisfied, a retry firing when the first attempt seemed to work, state being set to the value it already holds. Instinct says "this is a redundant no-op, I'll remove it." You remove it, run local tests (which may even pass if coverage is thin), push to CI, and a test fails with a title that describes exactly the behavior you just removed. The comment on that test explains a subtle platform bug or race condition that required the "redundant" call as a workaround.
The log line you reacted to wasn't evidence of a bug. It was evidence of the workaround executing correctly for the exact scenario it was designed for.
Context / Trigger Conditions
Apply this skill's caution when ANY of these hold:
- Redundant-looking call: You're about to wrap a call in
if (!already_X)or delete it outright because logs show it firing whenXis already true. - Impossible state in logs: Logs show a state combination that seems
logically impossible or contradictory (
playing=true+positionMs=0for seconds,isLoading=false+ data still empty, etc.). - "Why would anyone write this?": Reading code and you can't imagine a reason for a defensive check, extra await, or secondary call.
- Simplifying a conditional: A branch looks dead because you believe the condition can't be reached, or both branches look identical to you.
- Receiving a failing test: CI returns a failure with a test title that names exactly the behavior your change removed or modified.
Solution
Before touching the "redundant" code, run this five-step check:
Step 1: Grep for tests that assert the exact behavior
Search the test suite for the function name, the state you think is redundant, and any synonyms:
# Example: considering removing player.play() on rebuffer complete
grep -rn "player.play" test/ | grep -iE "already|even when|still|twice|redundant"
grep -rn "rebuffer.*play\|playing.*true.*play" test/
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 · 200 lines · 240 tokens per session scan A 695003dbc3a8
tests-guard-intentional-workarounds is a skill published in the GitHub repository divinevideo/divine-mobile (264 stars, last pushed today), licensed MPL-2.0. It adds 240 tokens to every session and 2,159 once invoked, about $0.0010 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 2026-09-03.
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".
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.
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.