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/openagentsinc/openagents/test-reportsnpx skills add OpenAgentsInc/openagents --skill test-reportsgit clone --depth 1 https://github.com/OpenAgentsInc/openagentsWhat 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 | $0.00055 | $0.00807 |
| Opus 5 | $0.00028 | $0.00404 |
| Sonnet 5 | $0.00011 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
test-reports 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 2d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test reports: pay for the suite once
A full-suite run costs minutes. A grep over its report costs milliseconds. The difference is whether the run left behind something addressable.
The rule
Whenever you run a suite that can fail — and you did not just run it seconds ago and watch it pass — write the machine-readable report to disk next to the raw output. Then every follow-up question ("which tests failed?", "was X among them?") is answered from the file, never from a second execution.
Long commands in this session already keep their whole output as a cmd-N.log
in the session directory; the result names the path. A structured report beats
grepping that log, because it holds failure names as data instead of terminal
rendering.
Canonical invocations
vitest / vp (TypeScript)
vp test --run --reporter=json --outputFile=/tmp/vitest-last.json 2>&1 | tail -20
Failing tests:
jq -r '.testResults[].assertionResults[] | select(.status=="failed") | .fullName' /tmp/vitest-last.json
One file's failures only:
jq -r --arg f thresholds.test.ts '.testResults[] | select(.name|contains($f)) | .assertionResults[] | select(.status=="failed") | .fullName' /tmp/vitest-last.json
(npx vitest … takes the same flags when a package does not expose vp.)
cargo (Rust)
cargo test 2>&1 | tee /tmp/cargo-test-last.log | tail -5
The JUnit form, where the reporter is available:
cargo test -- --format json > /tmp/cargo-test-last.json 2>/dev/null || cargo test 2>&1 | tee /tmp/cargo-test-last.log | tail -5
Failing tests:
grep -E '^test .* FAILED' /tmp/cargo-test-last.log
Then re-run nothing: each failing name sits on its own line with its module path, which is what you needed.
pytest (Python)
python -m pytest -q --junitxml=/tmp/pytest-last.xml 2>&1 | tail -5
Failing tests:
xpath -q -e '//failure/ancestor::testcase/@classname | //failure/ancestor::testcase/@name' /tmp/pytest-last.xml 2>/dev/null \
|| python3 -c "import xml.etree.ElementTree as ET; [print(t.get('classname'), t.get('name')) for t in ET.parse('/tmp/pytest-last.xml').getroot().iter('testcase') if t.find('failure') is not None]"
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.
- 2d ago First seen · 92 lines · 55 tokens per session scan A 2c1b37d7ea5c
test-reports is a skill published in the GitHub repository OpenAgentsInc/openagents (446 stars, last pushed 2d ago), licensed Apache-2.0. It adds 55 tokens to every session and 807 once invoked, about $0.0003 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.