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-manual-testing/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-manual-testing)<a href="https://agentmods.dev/skills/nerds-odd-e/doughnut/dough-manual-testing"><img src="https://agentmods.dev/badge/skills/nerds-odd-e/doughnut/dough-manual-testing/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-manual-testing"><img src="https://agentmods.dev/badge/skills/nerds-odd-e/doughnut/dough-manual-testing.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 | $0.00058 | $0.00872 |
| Opus 5.5 | $0.00023 | $0.00349 |
| Sonnet 5.5 | $0.00012 | $0.00174 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
dough-manual-testing 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 7d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Observe requested behavior
Use only on explicit developer request or plan-slice manual testing. No diagnosis, product repair, or unrequested tooling.
Mission
Resolve scope and time budget from the request: a feature, story set, recent deliveries, or change range. Recover current promises, examples, and constraints from this project's records or Git history, including deleted stories. Apply later decisions before older expectations; implementation, narration, and existing tests are not the oracle.
Identify in-scope externally observable surfaces, including non-web. Resolve URLs, accounts, startup, secrets, and tools from this project's guidance when needed; do not guess credentials.
If oracle, budget, or needed environment or access is missing, name it and stop; do not invent them.
A standalone session the developer accepts is a mission:
admit it before
setup or exploration, approach unselected, unless explicitly selected as
one-shot work. Observation
required by an active plan slice or story continues under that story.
Admission changes none of the testing-only limits here.
Plan
Before acting, list coverage areas and journeys, risks or questions, and proportional split of preparation, breadth, selective depth, and surprise/confirmation reserve. Weight by importance and risk. Include each promised surface. Completing this plan is not acceptance.
When a slice requires a developer-operated observation, take its question, rounds, and developer-performed steps from the slice and ask once for the set, not round by round; see plan and reuse developer-operated observation.
Prepare
For a standalone session that needs a project checkout, first read and follow the shared exploration workspace lifecycle. Enter that lifecycle before checkout-bound setup and use its selected checkout throughout the session.
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.
- 7d ago Changed · +5 lines b777e3a4ec4e
- 1mo ago Changed · +1 lines c0072cf6a381
- 1mo ago Changed · +1 lines 3cd3ba1886c8
- 1mo ago Changed · +8 lines d9b2bfcbfeb5
- 1mo ago Changed · -17 lines fd408f8b1038
- 1mo ago Changed · +26 lines e9d9d84e7ab2
- 1mo ago First seen · 67 lines · 58 tokens per session scan A 7424fe3b0212
dough-manual-testing is a skill published in the GitHub repository nerds-odd-e/doughnut (50 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 872 once invoked, about $0.0002 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 2026-09-17.
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.