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 agentmods add agents/jonapoul/aktual/gradle-runnergit clone --depth 1 https://github.com/jonapoul/aktualWrote 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/agents/jonapoul/aktual/gradle-runner)<a href="https://agentmods.dev/agents/jonapoul/aktual/gradle-runner"><img src="https://agentmods.dev/badge/agents/jonapoul/aktual/gradle-runner.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.00523 |
| Opus 5 | $0.00021 | $0.00262 |
| Sonnet 5 | $0.00008 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
gradle-runner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Gradle Runner
Run a single Gradle command and return only the actionable output (errors, failures, warnings). This keeps the parent context window clean by absorbing verbose Gradle noise in an isolated agent.
Execution
Parse the caller's prompt for the Gradle task(s) to run and any extra flags, then run via the wrapper script which handles output capture, filtering, and exit-code propagation:
./scripts/gradle-run.sh <tasks> [flags]
Common invocations
# Compile one module (most common)
./scripts/gradle-run.sh :<module>:compileAll
# Run tests for one module — `:<module>:test` is AMBIGUOUS in this project; use a
# concrete task: `testAll`, `testAndroidHostTest`, or `testAndroid`
./scripts/gradle-run.sh :<module>:testAndroidHostTest --continue
# Format check
./scripts/ktfmt.sh check 2>&1 | grep -v "^$" | head -50
Timeout
Always pass timeout: 600000 (10 minutes) to the Bash tool for all Gradle commands.
Rules
- Run Gradle commands sequentially, one Bash call at a time — never in parallel
- Report every command the caller asked for, separately and explicitly — state each one's outcome (succeeded / failed) even when an earlier or later command fails. Never collapse the report down to just the failing command; a silent omission reads to the caller as "didn't run"
- Report filtered output verbatim to the caller
- If a task name is ambiguous (Gradle replies "task '...' is ambiguous ... Candidates are: ..."), report the failure AND list the candidate task names verbatim so the caller can pick one — do not guess and re-run
- Do not attempt to fix issues — only report findings
- Do not read or modify source files
- Do not run
./gradlew buildor./gradlew allTests— those are full-project builds and will peg the machine
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.
- 3d ago First seen · 54 lines · 42 tokens per session scan A 3f863da76a64
gradle-runner is an agent published in the GitHub repository jonapoul/aktual (33 stars, last pushed 2d ago), licensed Apache-2.0. It adds 42 tokens to every session and 523 once invoked, about $0.0002 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 2026-09-01.
Other agents, from other repositories
kotlin-expert
Expert in Kotlin programming language, focusing on idiomatic Kotlin code, coroutines, extension functions, and memory management.
mobile-developer
Cross-platform mobile development specialist for React Native and Flutter. Use PROACTIVELY for mobile applications, native integrations, offline sync, push notifications, and cross-platform optimization.
Comet Squad
AI team for Comet MVU framework development. Manages the src/Comet subproject.
m3-expressive-guide
Material 3 Expressive design specialist. Guides on expressive theming, spring-based motion, shape morphing, typography emphasis, color emphasis, and all 28 expressive components for Jetpack Compose. Use when building modern, expressive Android UI.
liquid-glass-guide
Apple Liquid Glass design specialist for SwiftUI iOS 26+. Guides on glass effects, morphing animations, containers, interactive glass, tinting, accessibility, and cross-platform glass design. Use when building modern Apple UI with Liquid Glass.
accessibility-reviewer
Reviews Android Compose / iOS SwiftUI changes for screen-reader and reduce-motion regressions. Use proactively after any UI change, before opening a PR that touches ui/ or iosApp/ Views, or when asked to check TalkBack/VoiceOver accessibility. A core user base is blind and visually impaired — accessibility is treated…