A command that runs the project's complete automated test suite and reports any failed tests. It waits for a background test run to finish and does not change the code.

Use it to check the exif-turbo project before changes or a release, and to identify failing tests.

It avoids ending the check before long-running tests have completed. It also prevents accidental attempts to fix failures during the test run.

How baddonkey/exif-turbo configures GitHub Copilot

Reuse

Borrowing it

Nothing to install: this file belongs to baddonkey/exif-turbo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/baddonkey/exif-turbo/main/.github/prompts/run-tests.prompt.md

Clone the repo

git clone --depth 1 https://github.com/baddonkey/exif-turbo

Made for: GitHub Copilot.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/baddonkey/exif-turbo/run-tests/github.svg)](https://agentmods.dev/commands/baddonkey/exif-turbo/run-tests)

Your own site

<a href="https://agentmods.dev/commands/baddonkey/exif-turbo/run-tests"><img src="https://agentmods.dev/badge/commands/baddonkey/exif-turbo/run-tests/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/baddonkey/exif-turbo/run-tests"><img src="https://agentmods.dev/badge/commands/baddonkey/exif-turbo/run-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 771 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00021	$0.00771
Opus 5.5	$0.00008	$0.00308
Sonnet 5.5	$0.00004	$0.00154
Haiku 4.5	$0.00002	$0.00077

Measured 15d ago against content hash 892b38463ce6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Run tests 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 15d 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.

.github/prompts/run-tests.prompt.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the complete exif-turbo test suite and report the failed tests. Follow these steps exactly. Do not change any code, do not try to fix failures, and do not run pytest in any other way.

Rules

Use only the two commands below, in the terminal in sync mode, without a timeout. Run one command at a time, never in parallel.
Never run a long blocking command (pytest, --wait --max-wait <large>): the terminal returns early from commands running longer than ~10 s and then stays busy. The wait command blocks for only 8 s, so it always completes.
The commands Set-Location to the repo root first, because the terminal's working directory is not guaranteed.
Decide what to do next only from the last RUN-STATUS: line in the output. Do not rely on the exit code; the terminal does not always report it.
Do not end your turn while the status is STARTED or STILL_RUNNING.

Steps

1. Start the run

Set-Location "${workspaceFolder}"; & .\.venv\Scripts\python.exe scripts\run_tests_logged.py --detach

RUN-STATUS: STARTED: the run is going in the background. Go to step 2.
RUN-STATUS: STILL_RUNNING: a run is already in progress. Do not start another one; go to step 2 to follow it.
If a low-disk-space WARNING is printed, mention it in the final report.

2. Wait for completion (repeat)

Set-Location "${workspaceFolder}"; & .\.venv\Scripts\python.exe scripts\run_tests_logged.py --wait

Each call blocks for at most 32 seconds. A full run takes several minutes, so expect to repeat this command many times (dozens); that is normal.

Last line	Action
`RUN-STATUS: STILL_RUNNING`	Run the same command again right away. Do not comment on progress between calls.
`RUN-STATUS: PASSED`	Go to step 3.
`RUN-STATUS: FAILED`	Go to step 3.
`RUN-STATUS: RUNNER_DEAD`	Go to step 3; report that the runner died and quote the last lines of the `pytest.log` it names.
`RUN-STATUS: NO_RUN`	Go back to step 1.
No `RUN-STATUS` line / garbled output (e.g. `CommandNotFoundException`)	Run the same wait command again. It is always safe to repeat.

Read the full file on GitHub · 69 lines

Changes

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.

15d ago First seen · 69 lines · 21 tokens per session scan A 892b38463ce6

Subscribe to this mod's changes

Run tests is a command published in the GitHub repository baddonkey/exif-turbo (11 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 771 once invoked, about $0.0001 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 2026-10-14.

Testing

prototype

You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.

grainulation/grainulator · 0 tokens

qa-changes

This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…

OpenHands/extensions · 63 tokens

exif-turbo: Command for GitHub Copilot