Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ofcskn/mobile-automation-pluginnpx agentmods add commands/ofcskn/mobile-automation-plugin/msd-releaseWrote 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/commands/ofcskn/mobile-automation-plugin/msd-release)<a href="https://agentmods.dev/commands/ofcskn/mobile-automation-plugin/msd-release"><img src="https://agentmods.dev/badge/commands/ofcskn/mobile-automation-plugin/msd-release/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.
<a href="https://agentmods.dev/commands/ofcskn/mobile-automation-plugin/msd-release"><img src="https://agentmods.dev/badge/commands/ofcskn/mobile-automation-plugin/msd-release.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00013 | $0.01124 |
| Opus 5.5 | $0.00005 | $0.00450 |
| Sonnet 5.5 | $0.00003 | $0.00225 |
| Haiku 4.5 | $0.00001 | $0.00112 |
Grade A, and why
msd-release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the complete automobileapp release pipeline for the specified app.
Gate 0 — Credential check (run before anything else)
Step 0a — Auto-load credentials
Check for a local credentials file and source it silently if present:
# Auto-source .env.production if it exists (values never printed)
if [ -f ".env.production" ]; then
set -a && source .env.production && set +a
echo "✅ Loaded credentials from .env.production"
fi
If .env.production is not found, check whether EAS cloud secrets cover the required vars by running:
eas secret:list 2>/dev/null | grep -E "EXPO_TOKEN|APP_STORE|GOOGLE_SERVICES"
EAS cloud secrets are injected automatically during eas build and eas submit — if they appear here, no local env vars are needed.
Step 0b — Validate credentials
Load skills/submitting-app-release/references/credentials-guide.md and run:
check() { [ -n "${!1}" ] && echo "✅ $1" || echo "❌ $1 missing"; }
check EXPO_TOKEN
check APP_STORE_CONNECT_API_KEY_ID
check APP_STORE_CONNECT_ISSUER_ID
check APP_STORE_CONNECT_API_KEY_CONTENT # iOS only
check GOOGLE_SERVICES_JSON # Android only
Validate formats per credentials-guide.md (key ID = 10 chars, issuer ID = UUID, key content has PEM header, Google JSON has type: service_account).
Confirm EAS accepts the token:
eas whoami
Step 0c — If credentials are missing
Do NOT stop the pipeline silently. Show this exact message and offer the two setup paths:
⛔ Submission will be blocked. Choose a setup path:
Path A — EAS secrets (recommended — works in CI, set once forever):
eas secret:push --scope project --env-file .env.production
Path B — local .env.production (local dev only):
cp skills/submitting-app-release/references/.env.production.example .env.production
# Fill in real values, then re-run msd-release
See: skills/submitting-app-release/references/credentials-guide.md
Ask: "Set up credentials now (I'll walk you through it), or continue without submission?" If the user wants to set up now, run /automobileapp:msd-setup-credentials. Otherwise continue — all gates except submission will still run and the release summary will be generated.
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.
- 1mo ago First seen · 126 lines · 13 tokens per session scan A aaf26f044979
msd-release is a command published in the GitHub repository ofcskn/mobile-automation-plugin (2 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 1,124 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 2026-08-31.
Other commands, from other repositories
release-sync
Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.
ship
Open a pull request for the current branch, drive it green, and merge it.
release
Cut a Major.Minor release from the Increment.
changelog
Export user-facing release notes from the version history (derived, never edits the ledger).
moodle-bump-version
You will bump the Moodle plugin version and wire the upgrade step.
launch
Prepare a release by validating the install surface.