agentmods.dev

compass-calendar: Command for GitHub Copilot

.github/prompts/macos-parity-loop.md

macos-parity-loop is a command for GitHub Copilot from KeepSoftwareSimple/compass-calendar. It costs 0 tokens per session (318 once invoked), scanned A, original, MIT.

A focused maintenance workflow for keeping a macOS app and its web version consistent. It limits work to one named maintenance item and checks the change before opening and merging a pull request.

In plain words
What is it for?
Use it to implement one macOS parity item, update its evidence, run strict verification, dispatch native UI tests, and prepare an automatically mergeable pull request.
Why use it?
It prevents unrelated work from entering the task and avoids claiming accessibility or acceptance behavior works without evidence. It also separates local checks from native macOS tests that must run on GitHub-hosted Macs.

Command for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt. Also seen: mentions AGENTS.md.

This is KeepSoftwareSimple/compass-calendar's own configuration. It tells GitHub Copilot how to work on compass-calendar itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything compass-calendar configures →

not rated 226repo today A scan 0 tokens original MIT
View source ↗ KeepSoftwareSimple/compass-calendar compasscalendar.com
Reuse

Borrowing it

Nothing to install: this file belongs to KeepSoftwareSimple/compass-calendar. 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/KeepSoftwareSimple/compass-calendar/main/.github/prompts/macos-parity-loop.md
Clone the repo
git clone --depth 1 https://github.com/KeepSoftwareSimple/compass-calendar

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.

agentmods badge for macos-parity-loop

README.md
[![agentmods](https://agentmods.dev/badge/commands/keepsoftwaresimple/compass-calendar/macos-parity-loop/github.svg)](https://agentmods.dev/commands/keepsoftwaresimple/compass-calendar/macos-parity-loop)
Your own site
<a href="https://agentmods.dev/commands/keepsoftwaresimple/compass-calendar/macos-parity-loop"><img src="https://agentmods.dev/badge/commands/keepsoftwaresimple/compass-calendar/macos-parity-loop/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.

agentmods 80×15 button for macos-parity-loop

Your own site · 80×15
<a href="https://agentmods.dev/commands/keepsoftwaresimple/compass-calendar/macos-parity-loop"><img src="https://agentmods.dev/badge/commands/keepsoftwaresimple/compass-calendar/macos-parity-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 318 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00318
Opus 5.5 $0.00000 $0.00127
Sonnet 5.5 $0.00000 $0.00064
Haiku 4.5 $0.00000 $0.00032

Measured yesterday against content hash 0c8262fab623, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

macos-parity-loop 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 yesterday.

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/macos-parity-loop.md · 35 lines

What it actually says

macOS parity maintenance loop agent

You are a scoped worker for native/web parity on Compass Calendar. You do not run the general AGENT_LOOP queue and you do not touch unrelated milestones.

Read first

  • AGENTS.md
  • docs/development/macos-parity-flow.md
  • docs/CI-CD/macos-parity-loop-routine.md
  • docs/acceptance/macos-parity/checkpoint.md
  • .agents/skills/ship/SKILL.md

Scope

Your launch prompt names one stableKey from docs/acceptance/macos-parity/maintenance-queue.json. Implement only that package. Update inventory evidence honestly. Never weaken assertions, widen timeouts, or mark accessibility behaviors passing from model state alone.

Verify and ship

  1. bun run verify --strict locally for everything you can.
  2. Native UI XCTest only on GitHub Macs: dispatch test-macos.yml with strict_verify=true when product code changes; download logs before ready.
  3. Open a draft PR with Fixes #4783 (or the linked child issue if one exists).
  4. Mark ready and run gh pr merge --auto once verify is satisfied.

Boundaries

  • No local desktop takeover or credential inspection.
  • Signed-in acceptance stays blocked until Tyler authorizes the test account.
  • Keep the frozen baseline commit in inventory.json; record incremental web changes in incremental-stream.json with reviewed watermarks.
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.

  1. yesterday First seen · 35 lines · 0 tokens per session scan A 0c8262fab623

Subscribe to this mod's changes

macos-parity-loop is a command published in the GitHub repository KeepSoftwareSimple/compass-calendar (226 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 318 tokens. 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 2026-11-07.

CI and CDDevOps and cloudE2E testingReactTestingTypeScriptcalendargooglegoogle-calendarnodejs
Related

macos-parity-loop compared with commands from other repositories

macos-parity-loop next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
macos-parity-loopKeepSoftwareSimple/compass-calendarCommand226todayMITA0GitHub Copilot
validate-auth-schemakriasoft/react-starter-kitCommand24k6d agoMITA0Claude Code
e2e-testingJNTMTMTM/eIslandCommand335yesterdayGPL-3.0A0Claude Code
verify-bugHoangNguyen0403/agent-skills-standardCommand583yesterdayMITA0Claude Code
security-auditRewritingTheCode/workshopCommand122d agoMITA17Claude Code
checklistgithub/spec-kitCommand148kyesterdayMITA13Claude Code
clarifygithub/spec-kitCommand148kyesterdayMITA27Claude Code