Borrowing it
Nothing to install: this file belongs to allenhutchison/obsidian-gemini. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/allenhutchison/obsidian-gemini/master/.agents/skills/eval-harness/SKILL.mdgit clone --depth 1 https://github.com/allenhutchison/obsidian-geminiWrote 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/allenhutchison/obsidian-gemini/eval-harness)<a href="https://agentmods.dev/skills/allenhutchison/obsidian-gemini/eval-harness"><img src="https://agentmods.dev/badge/skills/allenhutchison/obsidian-gemini/eval-harness/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/allenhutchison/obsidian-gemini/eval-harness"><img src="https://agentmods.dev/badge/skills/allenhutchison/obsidian-gemini/eval-harness.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 Excessive Agency · line 178 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00137 | $0.03215 |
| Opus 5 | $0.00068 | $0.01607 |
| Sonnet 5 | $0.00027 | $0.00643 |
| Haiku 4.5 | $0.00014 | $0.00321 |
Grade A, and why
eval-harness 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 10d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval harness — run, monitor, bless
This skill drives npm run eval against a live Obsidian instance, watches for the failure modes we've actually hit in practice, and treats baseline blessing as a quality gate rather than a rubber stamp.
The harness itself is documented operationally in evals/README.md. This skill is the agent-side procedure for using it without producing corrupted baselines or leaving orphaned state behind.
When to use this skill
- The user wants to run the eval harness — full sweep, single task, or model sweep
- The user wants to bless a result as the baseline for a (provider, model) pair
- The user wants to measure the impact of a change on the eval suite (run, compare against baseline, decide)
- A new pinned model has shipped and we want a baseline for it
Don't use this skill for:
- Editing tasks or fixtures — that's regular development work, just edit
evals/tasks/andevals/fixtures/directly - Investigating a single failed task in isolation —
npm run eval -- --task=<id>once is enough; no skill orchestration needed
Vault guard (mandatory preflight)
The harness drives the agent view, creates eval-scratch/ fixtures in the vault, and may temporarily change settings.chatModelName. Running it against the wrong vault would dirty the user's actual notes.
The Obsidian CLI's vault=<name> flag does not actually route by name — it always targets the focused window. So before running any obsidian or npm run eval command, ask the user to prepare Obsidian and wait for confirmation:
Before I start the eval run, please prepare Obsidian:
- Close every vault except the test vault. Focus can drift mid-run; the only safe posture is to have just the test vault open.
- Open the test vault (default:
Test Vault) and make it the focused window.- Open the agent view pane (Gemini Scribe ribbon icon, or palette → "Open Agent View"). The harness drives this view; if it's not visible you won't see activity, but the run still drives the model.
- Save and close any unsaved work — fixtures get planted into
eval-scratch/and torn down per task.Reply "ready" once Obsidian has only the test vault open and focused.
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.
- 10d ago First seen · 250 lines · 137 tokens per session scan A 974f91aeff5a
eval-harness is a skill published in the GitHub repository allenhutchison/obsidian-gemini (524 stars, last pushed today), licensed MIT. It adds 137 tokens to every session and 3,215 once invoked, about $0.0007 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
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.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.