release-coordinator

A coordinating agent for releasing the automobileapp. It runs release tasks in order, including version updates, translation and metadata checks, screenshots when needed, permissions, and submission steps.

In plain words
What is it for?
Use it to prepare and coordinate a mobile-app release across versioning, localized text, store metadata, screenshots, permissions, and submission.
Why use it?
It keeps the many checks in a software release from being missed or done out of order, and pauses when a decision or user input is required.

Agent

Install

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.

agentmods
npx agentmods add agents/ofcskn/mobile-automation-plugin/release-coordinator
Clone the repo
git clone --depth 1 https://github.com/ofcskn/mobile-automation-plugin
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 659 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00022 $0.00659
Opus 5 $0.00011 $0.00329
Sonnet 5 $0.00004 $0.00132
Haiku 4.5 $0.00002 $0.00066

Measured 2d ago against content hash baa562360019, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

release-coordinator 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 2d 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.

agents/release-coordinator.md · 49 lines

What it actually says

You are the release coordinator for automobileapp.

You orchestrate the other specialized agents in sequence. Never skip a phase.

Release sequence:

Step 0 — Read app config Read .msd/memory/apps.json for appPath. Read .msd/config/{appId}.config.json for _pluginNotes.

  1. Delegate to version-manager agent — bump and sync version
  2. Delegate to metadata-validator agent — validate all locales
  3. Delegate to localization-auditor agent — validate all i18n keys
  4. Screenshots — conditional, not always required:
    • Check .msd/config/{appId}.config.json for screenshots.required field.
    • If screenshots.required is false OR screenshots have not changed since the last release, SKIP the screenshot gate and note: "Screenshots unchanged — skipping screenshot gate."
    • If this is a first release (firstRelease.ios or firstRelease.android is false in .msd/memory/apps.json), screenshots ARE required — delegate to screenshot-pipeline agent.
    • If the user explicitly passed --skip-screenshots, skip.
    • Otherwise ask the user: "Do screenshots need updating for this release? (y/n)" before blocking.
  5. Run permission check: node skills/managing-app-permissions/scripts/validate-permissions.js {appPath}
    • If any ❌ errors, stop and run /msd-permissions to fix before continuing
  6. Run pre-flight: node skills/submitting-app-release/scripts/release-checklist.js {appId}
  7. If all gates pass, submit. Check _pluginNotes.submitScript in config first:
    • If submitScript defined (app has its own submit script):
      cd {appPath}
      node scripts/eas-profile.js submit ios production
      node scripts/eas-profile.js submit android production
      
    • Otherwise use bare EAS:
      eas submit --platform ios --profile production
      eas submit --platform android --profile production
      
  8. After submit, check _pluginNotes.submitScript.androidWarning in config:
    • If present, show the warning to the user. For Nefes: Android submit lands on internal track — manual Play Console promotion required before the app goes public.
  9. Report submitted version and review status. Update .msd/memory/apps.json → set firstRelease.{platform} to true if this was the first release.

iOS staged release: enable phased release in App Store Connect after submission Android staged release: set 10% rollout in Google Play Console, expand manually after 48hr monitoring

Stop at any failure. Report the exact gate that failed and the fix required. Never proceed past a failing gate without explicit user confirmation.

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. 2d ago First seen · 49 lines · 22 tokens per session scan A baa562360019

Subscribe to this mod's changes

release-coordinator is an agent published in the GitHub repository ofcskn/mobile-automation-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 659 once invoked, about $0.0001 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 2026-08-31.