Borrowing it
Nothing to install: this file belongs to AshotN/OpenCode-Relay. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AshotN/OpenCode-Relay/master/.opencode/skills/writing-test-with-trace/SKILL.mdgit clone --depth 1 https://github.com/AshotN/OpenCode-RelayWrote 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/ashotn/opencode-relay/writing-test-with-trace)<a href="https://agentmods.dev/skills/ashotn/opencode-relay/writing-test-with-trace"><img src="https://agentmods.dev/badge/skills/ashotn/opencode-relay/writing-test-with-trace/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/ashotn/opencode-relay/writing-test-with-trace"><img src="https://agentmods.dev/badge/skills/ashotn/opencode-relay/writing-test-with-trace.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 | $0.00024 | $0.01036 |
| Opus 5.5 | $0.00010 | $0.00414 |
| Sonnet 5.5 | $0.00005 | $0.00207 |
| Haiku 4.5 | $0.00002 | $0.00104 |
Grade A, and why
Write test based on trace 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 2mo 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core
The user has experienced an issue. They followed a series of steps with the plugin and something went wrong. With their explanation in mind, read the latest trace log and create a test that captures the issue. The test must fail before any fix is applied.
Trace files
Use a explore sub-agent to find the most recent trace
Trace files are written under Java's temp directory, not necessarily literal /tmp. The code uses
Path.of(System.getProperty("java.io.tmpdir"), "opencode-diff-traces").
On macOS this often resolves to a sandboxed path such as
/var/folders/.../T/opencode-diff-traces, even though users may describe it as /tmp. Do not
assume /tmp/opencode-diff-traces exists before checking how java.io.tmpdir was resolved for the
running IDE instance.
If the user ran the plugin from Gradle's Run Plugin configuration, check the sandbox IDE log
first to find the exact trace file path. In this repo that is typically
build/idea-sandbox/IU-*/log/idea.log. Search for:
JsonlDiffTracer: tracing enabled file=failed to create trace directoryfailed to open trace file
Use that log line to locate the exact JSONL trace file before reading it. Once you know the
directory, list it to find the most recent file (sorted by modification time). Check its line count
with wc -l before reading. If it is small (under a few hundred lines), read it in full with
cat. If it is large, use grep to filter by the kind values relevant to the issue, or read the
tail with tail -n N to focus on the most recent events.
Each line is a JSON object. Read events in seq order. Each event has a kind, a sessionId
inside fields, and additional fields that vary by kind. Read the fields that are present and
reason from them — do not assume which fields will be relevant before reading.
Identifying the root cause
Do not jump to conclusions. Read the trace in full first, then reason from what you observe.
Describe what the trace shows and compare it against what the user expected to happen. The gap between those two things is the bug. Only after identifying the gap should you form a hypothesis about the cause.
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.
- 2mo ago First seen · 110 lines · 24 tokens per session scan A 72d9600ccf90
Write test based on trace is a skill published in the GitHub repository AshotN/OpenCode-Relay (23 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 1,036 once invoked, about $0.0001 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
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
observability-langsmith
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
reenable-test
Guide for investigating, fixing, verifying via TDD, and re-enabling disabled or flaky Chromium tests (C++, Android Java, or WebUI). Use this skill when asked to deflake, fix, or re-enable a disabled or flaky test case, or to verify post-submit stability of a re-enabled test. Don't use for disabling a failing test…
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
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.…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.