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 AURORA-NEURO/aurora-agent --skill windows-test-truthgit clone --depth 1 https://github.com/AURORA-NEURO/aurora-agentWrote 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/aurora-neuro/aurora-agent/windows-test-truth)<a href="https://agentmods.dev/skills/aurora-neuro/aurora-agent/windows-test-truth"><img src="https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/windows-test-truth/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/aurora-neuro/aurora-agent/windows-test-truth"><img src="https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/windows-test-truth.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 | $0.00077 | $0.00464 |
| Opus 5 | $0.00039 | $0.00232 |
| Sonnet 5 | $0.00015 | $0.00093 |
| Haiku 4.5 | $0.00008 | $0.00046 |
Grade A, and why
windows-test-truth 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 9d 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.
What it actually says
Windows test truth (os error 4551)
Windows Application Control sometimes blocks a freshly linked binary. The symptom in Rust is:
error: test failed ... (os error 4551)
The binary never executed. This is not a failing test — the suite NEVER RAN. Two consequences:
- A suite that never ran looks like a suite that failed.
cargo test --workspacekeeps going and its final total silently loses every test in and after the blocked binary. One real run reported 344 tests where the true figure was 4,327.
The recipe
Force a relink (a new binary usually passes) and prove the count is complete:
find crates -name '*.rs' -path '*/tests/*' -exec touch {} +
cargo test --workspace --offline --no-fail-fast 2>&1 | grep -c 'never executed'
cargo test --workspace --offline --no-fail-fast 2>&1 \
| grep -E '^test result: ok' | awk '{s+=$4} END {print s}'
A non-zero first number invalidates the second. If touching is not enough,
delete the stale test executable under target/ so the linker must produce a
fresh one.
Related lies to watch for
- The same block can hit any freshly built executable, not just tests — a packaged app that "won't start" with an Application Control message needs a pristine known binary or a policy allowance, not a rebuild loop.
- Never sum per-crate results while other agents are concurrently editing
crates: a crate mid-edit fails to compile and takes the whole invocation
down for reasons unrelated to your change. Test per-crate (
-p) in that situation.
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.
- 9d ago First seen · 47 lines · 77 tokens per session scan A b1e4ead359a2
windows-test-truth is a skill published in the GitHub repository AURORA-NEURO/aurora-agent (1 stars, last pushed today), licensed Apache-2.0. It adds 77 tokens to every session and 464 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
blazemeter-troubleshooting
Comprehensive troubleshooting guide for BlazeMeter, covering API Monitoring, Performance Testing, general issues, integrations, and security. Use when troubleshooting for (1) API Monitoring issues (Radar Agent auth, SSL certificates, debug tests), (2) Performance Testing issues (high response time, 500 errors, partial…
qa
QA test a live website with Axon discovery/content evidence plus browser automation when interaction is required. Use when the user wants exploratory QA, form testing, navigation/link checks, responsive checks, performance observations, bug reports, or a pre-launch quality review.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, then fills the gaps with list (filters, sort, a time…
opik-explain
Root-cause a specific Opik trace, or a pattern across traces, and return a grounded explanation. Uses the hosted Opik MCP when it is connected, and falls back to SDK scripting otherwise. Returns the root cause, the evidence spans as clickable Opik UI links, and one suggested next step. Use for "why did this trace…
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
blazemeter-performance-testing
Comprehensive guide for BlazeMeter Performance Testing, including load configuration, reporting, JMeter configuration, Taurus, scenarios, and advanced features. Use when working with Performance tests for (1) Configuring load settings and distribution, (2) Creating and running tests (JMeter, Browser, URL/API…