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 8Dionysus/aoa-skills --skill aoa-evalgit clone --depth 1 https://github.com/8Dionysus/aoa-skillsWrote 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/8dionysus/aoa-skills/aoa-eval)<a href="https://agentmods.dev/skills/8dionysus/aoa-skills/aoa-eval"><img src="https://agentmods.dev/badge/skills/8dionysus/aoa-skills/aoa-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/8dionysus/aoa-skills/aoa-eval"><img src="https://agentmods.dev/badge/skills/8dionysus/aoa-skills/aoa-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 | $0.00068 | $0.01182 |
| Opus 5 | $0.00034 | $0.00591 |
| Sonnet 5 | $0.00014 | $0.00236 |
| Haiku 4.5 | $0.00007 | $0.00118 |
Grade A, and why
aoa-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 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aoa-eval
Intent
Route one evaluation need to the narrowest procedure that preserves its real owner, input contract, output, and proof limit. Consolidation here is a shared front door, not a collapse of five different capabilities into generic prose.
Trigger boundary
Use this skill when:
- an eval surface must be selected or applied
- an established no-fit needs a local intake packet or a bounded suite design
- researched eval-trigger classes and supplied or retrieved session hits need eval-owned candidate classification
Do not use this skill when:
- the task is an ordinary test run, the invariant is still unknown, the real need is generic session harvesting, or the requested effect is central proof promotion
Inputs
- one mode intent plus its owner, source ref, acceptance target, relevant evidence or inventory, effect authority, and required environment details
Outputs
- one mode-specific result defined by
references/contract.yaml, including owner, evidence class, proof limit, next route, and stop line
Procedure
Record <bundle_dir> as the directory containing this loaded SKILL.md.
Choose exactly one mode
| Mode | Use when | Required procedure |
|---|---|---|
select |
No exact evidence surface has been selected. | references/select.md |
apply |
The exact surface and acceptance contract are explicit. | references/apply.md |
local-need |
Selection proved no fit and an existing local eval port should receive pressure. | references/local-need.md |
design |
Selection proved no fit and a stable invariant needs a bounded local suite or report design. | references/design.md |
session-mining |
Prior research defined eval-trigger classes that need real session examples. | references/session-mining.md |
Mode: select
Read and follow references/select.md.
Mode: apply
Read and follow references/apply.md.
Mode: local-need
Read and follow references/local-need.md.
Mode: design
What ships with it
8 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.
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 · 135 lines · 68 tokens per session scan A e1afc4872221
aoa-eval is a skill published in the GitHub repository 8Dionysus/aoa-skills (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,182 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 2026-08-31.
Other skills, from other repositories
pptx-html-fidelity-audit
Audit a python-pptx export against its source HTML deck, identify layout/content drift (footer overflow, cropped content, missing italic/em, lost styling, off-rhythm spacing), and re-export with strict footer-rail + cursor-flow layout discipline. Use this skill whenever the user has a .pptx that was generated from an…
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
nemo-automodel-model-onboarding
Guide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.
amc-run-sample-calibration
Run end-to-end calibration on the shipped sample dataset (sdg082sampledata010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.
jetson-video-pipeline
Use when executing and verifying Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or acceptance workflows with exact artifact handoffs.
nemo-automodel-recipe-development
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.