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 processmission/oh-my-qemu --skill qemu-model-verificationgit clone --depth 1 https://github.com/processmission/oh-my-qemuWrote 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/processmission/oh-my-qemu/qemu-model-verification)<a href="https://agentmods.dev/skills/processmission/oh-my-qemu/qemu-model-verification"><img src="https://agentmods.dev/badge/skills/processmission/oh-my-qemu/qemu-model-verification/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/processmission/oh-my-qemu/qemu-model-verification"><img src="https://agentmods.dev/badge/skills/processmission/oh-my-qemu/qemu-model-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 123 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00052 | $0.01446 |
| Opus 5 | $0.00026 | $0.00723 |
| Sonnet 5 | $0.00010 | $0.00289 |
| Haiku 4.5 | $0.00005 | $0.00145 |
Grade A, and why
qemu-model-verification 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 11d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QEMU Model Verification
Audit workflow
For non-trivial workspace writes, use a stable
.oh-my-qemu/<task-slug>/ directory and create only needed entries:
.oh-my-qemu/<task-slug>/
├── audit.md # Baseline, scope, decisions, evidence, verification, and gaps
├── commands.md # Redacted commands, working directories, and results
├── logs/ # Decisive build, test, runtime, or diagnostic logs
├── scripts/ # Temporary scripts, probes, parsers, and harnesses
└── output/ # Generated deliverables, dependencies, and non-QEMU binaries
Before changing source or mutable artifacts, record the workspace root,
revision, git status --short, pre-existing changes, goal, scope, and
acceptance checks in audit.md. Log exact redacted commands and results in
commands.md; record revisions, configurations, tool versions, and hashes when
they affect reproducibility. Separate observations from inferences and edit
source only when requested.
Keep QEMU builds under source-root builds/build-<target>/; put third-party
dependencies and non-QEMU binaries in task output/. Before writing audit
artifacts or configuring QEMU in a Git worktree, add .agents/,
.oh-my-qemu/, and builds/ to the repository-local file from
git rev-parse --git-path info/exclude; preserve existing entries and avoid
duplicates. Never stage or commit those directories. At handoff, verify them
absent from git status --short. Report the task directory and unresolved gaps.
QEMU upstream boundary
QEMU's official GitLab and mailing lists are upstream project channels. A
patch becomes an upstream contribution when sent to the mailing-list recipients
selected through MAINTAINERS; do not prepare or send agent-generated patches
for that submission. Local branches, commits, patch files, pushes, and pull
requests are not by themselves QEMU upstream contributions. Perform those Git
actions only when requested and follow the workspace's Git policy.
Evidence ladder
Given a falsifiable claim and existing evidence, report PASS, FAIL, or
INCONCLUSIVE without inventing missing evidence. Use the lowest rung that
proves the claim:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 163 lines · 52 tokens per session scan A 0e39ea5771b0
qemu-model-verification is a skill published in the GitHub repository processmission/oh-my-qemu (57 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 1,446 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
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
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.
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.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
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.
work
Deliver one maintainer-approved EmDash issue, choosing the bug-fix path for a defect and the direct implementation path for an enhancement or task.