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 agentmods add skills/ashotn/opencode-relay/writing-test-with-tracenpx skills add AshotN/OpenCode-Relay --skill writing-test-with-tracegit 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.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.01036 |
| Opus 5 | $0.00012 | $0.00518 |
| Sonnet 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 4d 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.
- 4d 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 4d ago), licensed MIT. It adds 24 tokens to every session and 1,036 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…