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 specula-org/SysMoBench --skill tv-evalgit clone --depth 1 https://github.com/specula-org/SysMoBenchWrote 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/specula-org/sysmobench/tv-eval)<a href="https://agentmods.dev/skills/specula-org/sysmobench/tv-eval"><img src="https://agentmods.dev/badge/skills/specula-org/sysmobench/tv-eval/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/specula-org/sysmobench/tv-eval"><img src="https://agentmods.dev/badge/skills/specula-org/sysmobench/tv-eval.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 | $0.00069 | $0.00190 |
| Opus 5.5 | $0.00028 | $0.00076 |
| Sonnet 5.5 | $0.00014 | $0.00038 |
| Haiku 4.5 | $0.00007 | $0.00019 |
Grade A, and why
tv-eval 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.
What it actually says
Read guide.md for the full workflow.
Reference docs:
references/canonical_window_format.md— the one true window file schemareferences/tv_module_template.md— how to write TV_.tlareferences/score_interpretation.md— how to explain pass rates
Worked examples:
examples/spin/— simple case (spinlock), 1 aux variableexamples/etcd/— complex case (etcd-raft), 4 aux variables, log abstraction
What ships with it
55 files 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.
- examples/etcd/action_windows.jsonl 149 KB
- examples/etcd/ai_spec_1/etcdraft.cfg 550 B
- examples/etcd/ai_spec_1/etcdraft.tla 17 KB
- examples/etcd/ai_spec_1/make_windows.py 2.0 KB runs code
- examples/etcd/ai_spec_1/run_tv.py 1.9 KB runs code
- examples/etcd/ai_spec_1/TV_ClientProposal.cfg 598 B
- examples/etcd/ai_spec_1/TV_ClientProposal.tla 1.6 KB
- examples/etcd/ai_spec_1/TV_ElectionTimeout.cfg 598 B
- examples/etcd/ai_spec_1/TV_ElectionTimeout.tla 1.6 KB
- examples/etcd/ai_spec_1/TV_HandleAppendEntries.cfg 598 B
- examples/etcd/ai_spec_1/TV_HandleAppendEntries.tla 2.9 KB
- examples/etcd/ai_spec_1/TV_HandleVoteRequest.cfg 598 B
- examples/etcd/ai_spec_1/TV_HandleVoteRequest.tla 2.3 KB
- examples/etcd/ai_spec_1/windows_ClientProposal.ndjson 12 KB
- examples/etcd/ai_spec_1/windows_ElectionTimeout.ndjson 4.3 KB
- examples/etcd/ai_spec_1/windows_HandleAppendEntries.ndjson 88 KB
- examples/etcd/ai_spec_1/windows_HandleVoteRequest.ndjson 11 KB
- examples/etcd/ai_spec_2/etcdraft.cfg 86 B
- examples/etcd/ai_spec_2/etcdraft.tla 17 KB
- examples/etcd/ai_spec_2/make_windows.py 2.4 KB runs code
- examples/etcd/ai_spec_2/TV_ClientRequest.cfg 108 B
- examples/etcd/ai_spec_2/TV_ClientRequest.tla 1.6 KB
- examples/etcd/ai_spec_2/TV_HandleAppendEntriesRequest.cfg 108 B
- examples/etcd/ai_spec_2/TV_HandleAppendEntriesRequest.tla 2.2 KB
- examples/etcd/ai_spec_2/TV_HandleVoteRequest.cfg 108 B
- examples/etcd/ai_spec_2/TV_HandleVoteRequest.tla 1.8 KB
- examples/etcd/ai_spec_2/windows_ClientRequest.ndjson 12 KB
- examples/etcd/ai_spec_2/windows_HandleAppendEntriesRequest.ndjson 83 KB
- examples/etcd/ai_spec_2/windows_HandleVoteRequest.ndjson 10 KB
- examples/etcd/generate_windows.py 6.3 KB runs code
- examples/etcd/HandleVoteRequest_report.md 2.9 KB
- examples/spin/action_windows.jsonl 2.9 KB
- examples/spin/ai_spec_1/make_windows.py 1.7 KB runs code
- examples/spin/ai_spec_1/run_tv.py 435 B runs code
- examples/spin/ai_spec_1/spin.cfg 54 B
- examples/spin/ai_spec_1/spin.tla 1.9 KB
- examples/spin/ai_spec_1/TV_AcquireLock.cfg 74 B
- examples/spin/ai_spec_1/TV_AcquireLock.tla 828 B
- examples/spin/ai_spec_1/windows_AcquireLock.ndjson 543 B
- examples/spin/generate_windows.py 6.7 KB runs code
- examples/spin/legacy/action_windows.jsonl 144 KB
- examples/spin/legacy/windows_AcquireLock.ndjson 37 KB
- examples/spin/reference_spec/run_tv.py 432 B runs code
- examples/spin/reference_spec/spin.cfg 101 B
- examples/spin/reference_spec/spin.tla 1.6 KB
- examples/spin/reference_spec/TV_Windows.cfg 69 B
- examples/spin/reference_spec/TV_Windows.tla 976 B
- examples/spin/traces/kernel-test.txt 1.1 KB
- examples/spin/traces/manifest.json 706 B
- examples/spin/traces/trace_01.jsonl 1.0 KB
- examples/spin/validate.py 3.2 KB runs code
- guide.md 16 KB
- references/canonical_window_format.md 4.6 KB
- references/score_interpretation.md 5.3 KB
- references/tv_module_template.md 4.3 KB
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 · 16 lines · 69 tokens per session scan A fc3515f72cbc
tv-eval is a skill published in the GitHub repository specula-org/SysMoBench (26 stars, last pushed 18d ago), licensed Apache-2.0. It adds 69 tokens to every session and 190 once invoked, about $0.0003 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
train-pose
Train/evaluate WiFi pose models honestly — camera-supervised (MediaPipe + CSI) and camera-free (WiFlow), always checked against the mean-pose baseline before any PCK is quoted.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
experiment-audit
A review step that checks whether an experiment's reported results are supported by real data and a sufficiently broad test.
i4h-catheter-navigation-e2e
End-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the v0.7 pipeline.
i4h-catheter-navigation-render-drr
Render a single DRR fluoroscopy frame from a CT cache or synthetic phantom. Use when asked to render DRR, generate a fluoro image, or smoke-test the Slang renderer.
i4h-catheter-navigation-smoke
Run CPU-only fluorosim smoke tests (imports, preprocessing, CLI parsers). Use when asked to smoke-test catheter navigation in CI or without a GPU.