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 instructions/costular/minitask/agents-mdgit clone --depth 1 https://github.com/costular/MinitaskWrote 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/instructions/costular/minitask/agents-md)<a href="https://agentmods.dev/instructions/costular/minitask/agents-md"><img src="https://agentmods.dev/badge/instructions/costular/minitask/agents-md.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 | $0.00679 | $0.00679 |
| Opus 5 | $0.00340 | $0.00340 |
| Sonnet 5 | $0.00136 | $0.00136 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
Minitask AGENTS.md 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 today.
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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
app/contains the Android app; unit and instrumentation suites sit undersrc/testandsrc/androidTest.core/*supplies shared UI, design, analytics, logging, notifications, andcore/testingutilities.feature/*hosts vertical slices (agenda, settings, detail, onboarding); keep new flows in their own feature module.data/handles repositories and persistence;common/tasksholds task-domain models.build-logic/ships custom Gradle convention plugins;screenshot_testing/,scripts/, andbenchmarks/cover snapshot + baseline tooling.
Build, Test, and Development Commands
./gradlew assembleDebugbuilds a debuggable APK../gradlew testDebugUnitTestruns JVM unit tests../gradlew connectedAndroidTestlaunches instrumentation tests withAtomTestRunner(device/emulator required)../gradlew detekt lintDebugenforces Kotlin + Android linting../scripts/verify-screenshots.shcompares Compose snapshots;record-screenshots.shrefreshes baselines.
Coding Style & Naming Conventions
- Kotlin uses the official style (
kotlin.code.style=official), 4-space indents, trailing commas when it aids diffs. - Prefer
PascalCasefor types,camelCasefor members,snake_casefor resources; Compose previews belong in*Preview.kt. - Keep modules isolated: share code through
core/common, not direct feature cross-deps. - Detekt (
atomtasks.detekt) runs locally and in CI; resolve warnings before pushing.
Testing Guidelines
- Co-locate unit tests with source modules and lean on
core/testingfor coroutine and Hilt helpers. - Place UI and integration suites in
src/androidTest; rely on Compose test APIs and stable semantics. - Snapshot updates need new images in
app/screenshots/andscreenshot_testing/, plus a PR note. - Aim for unit coverage on new logic and add an instrumentation or snapshot check for user-facing UI.
Commit & Pull Request Guidelines
- Commits stay short and imperative (
Fix hardcoded string,Update theme), referencing issues as(#123)when needed. - Rebase or tidy history before opening a PR; avoid merge commits.
- PR descriptions should state intent, local testing, and UI impact (attach screenshots or screencasts).
- Link issues, call out config or feature flag changes, and note any follow-up work.
- Add release-note-worthy changes to
CHANGELOG.mdunder## [Unreleased], using the existing Keep a Changelog categories and markdown format. - Do not manually promote
Unreleased, add release dates, or create the next emptyUnreleasedsection; the release workflow handles that when a tag is created, committing the promotion to a release pull request formain.
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.
- today First seen · 40 lines · 679 tokens per session scan A bbf96d23eeb8
Minitask AGENTS.md is an instructions file published in the GitHub repository costular/Minitask (12 stars, last pushed 7d ago), licensed Apache-2.0. It adds 679 tokens to every session, about $0.0034 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 2026-09-04.
Other instructions, from other repositories
SimpMusic CLAUDE.md
Claude Code instructions for maxrave-dev/SimpMusic, covering claude.md - simpmusic project guide for ai agents, 🌐 language rule, 📋 project overview, main purpose and basic information.
Amarok-Hider AGENTS.md
Instructions for deltazefiro/Amarok-Hider, covering amarok, project overview, build, e2e test and agent rules.
OpenTagViewer AGENTS.md
AGENTS.md instructions for parawanderer/OpenTagViewer, covering agents.md, what this project is, rules, 1. never ship a room schema change without a migration and 2. do not claim something works if you have not run it.
OpenTagViewer CLAUDE.md
Claude Code instructions for parawanderer/OpenTagViewer: The rules for this repo live in AGENTS.md, so that every agent reads the same file rather than two copies that drift apart. This one exists only to pull it in — Claude Code loads CLAUDE.md automatically, and the line below imports the real thing.
LastChat AGENTS.md
AGENTS.md instructions for Cocolalilal/LastChat, covering agents.md, project, modules (settings.gradle.kts), build and app architecture (:app).
apk-analyzer AGENTS.md
AGENTS.md instructions for MartinStyk/apk-analyzer, covering apk analyzer agent instructions, non-negotiables, development workflow, engineering principles and verifying a change.