Borrowing it
Nothing to install: this file belongs to nerds-odd-e/doughnut. 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/nerds-odd-e/doughnut/main/.agents/skills/dough-test-optimization/SKILL.mdgit clone --depth 1 https://github.com/nerds-odd-e/doughnutWrote 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/nerds-odd-e/doughnut/dough-test-optimization)<a href="https://agentmods.dev/skills/nerds-odd-e/doughnut/dough-test-optimization"><img src="https://agentmods.dev/badge/skills/nerds-odd-e/doughnut/dough-test-optimization/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/nerds-odd-e/doughnut/dough-test-optimization"><img src="https://agentmods.dev/badge/skills/nerds-odd-e/doughnut/dough-test-optimization.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 | $0.00063 | $0.01869 |
| Opus 5.5 | $0.00025 | $0.00748 |
| Sonnet 5.5 | $0.00013 | $0.00374 |
| Haiku 4.5 | $0.00006 | $0.00187 |
Grade A, and why
dough-test-optimization 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 1mo 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Speed up local test feedback
Reduce the time a developer waits for trustworthy local test results. Pursue substantial savings through fewer redundant cases, less setup and support code, and cleaner design together. These are ways to improve feedback time, not substitutes for a measured speedup. Preserve behavioral coverage and confidence.
Establish context and mode
Use the task's project. Resolve the selected local test command and scope, test locations, runtime/service setup, applicable test and architectural rules, and plan conventions from that project. Name genuinely missing context and stop only its dependent step; do not invent paths, commands, or a test taxonomy.
Default mode profiles, plans, experiments, and re-profiles. A profile-only request
ends with findings. For --resolve, follow only
candidate resolution.
An independently requested pass in any mode is an accepted mission:
admit it before
profiling or triage, with its story in a relevant existing seed when one fits
and approach unselected. A pass explicitly selected as
one-shot work follows that
instead. A pass requested as a step of an active story
continues under that story. Findings with no worthwhile change, in profiling
or resolve-only triage,
finish the mission,
or under one-shot its
no-change finish.
Before assessing tests, read the shared behavioral test guidance. Apply it across the authorized optimization scope, not just the current diff.
Establish the baseline
Run the selected local scope. Record revision, literal command, runner mode, workers, filters, relevant environment/cache conditions, wall time, executed case count, and available test/setup timings. Keep raw profiles out of commits. Use only approved profile exclusions; candidate proposals remain eligible and normal verification coverage stays intact. Report the limits of filtered runs.
What ships with it
2 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.
- 1mo ago Changed · +4 lines 8666f1c2f7d0
- 1mo ago Changed · +14 lines 50a3dd4fa71d
- 1mo ago Changed · +2 lines 74be61ea2d13
- 1mo ago Changed · +16 lines 425da73fca1f
- 1mo ago First seen · 126 lines · 63 tokens per session scan A 90f5005e5046
dough-test-optimization is a skill published in the GitHub repository nerds-odd-e/doughnut (50 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 1,869 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 2026-09-15.
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".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
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.