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 commands/vmobifystudio/app-dev-team/app-plangit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWhat 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 | $0.00017 | $0.01623 |
| Opus 5 | $0.00009 | $0.00812 |
| Sonnet 5 | $0.00003 | $0.00325 |
| Haiku 4.5 | $0.00002 | $0.00162 |
Grade A, and why
app-plan 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/app-plan — Plan the next sprint
Focus (optional): $ARGUMENTS
Steps
-
Confirm prerequisites exist:
docs/11-backlog.mdand at least onedocs/22-impl-spec-*.md. Plan against whatever platforms have a spec.Requiring both an iOS and an Android spec fails every single-platform project —
requirements-intakeasks "iOS, Android, or both" — and every brownfield project, whose specs arrive as/app-onboard's per-platformdocs/22-impl-spec-<platform>.mdsnapshots. Both were then told to run/app-init, which greenfield had just run and which/app-onboardexplicitly tells brownfield users not to run.If the backlog or every spec is missing, stop and name the missing file, then suggest
/app-initfor an empty directory or/app-onboardfor a directory that already has code. Never suggest/app-initon a project that has an app in it.
1a. Adopt the event log before adding anything to it. The board is now generated from
docs/31-board-events.jsonl; docs/31-board.md is its rendering. A project planned before this
existed has the board and not the log, and board.mjs add on that project would create a
one-ticket log and render over the hand-written board. So migrate first, once, and say so:
if [ ! -f docs/31-board-events.jsonl ] && [ -f docs/31-board.md ]; then
node "${CLAUDE_PLUGIN_ROOT}/scripts/board.mjs" migrate docs/31-board.md --out docs/31-board-events.jsonl \
&& node "${CLAUDE_PLUGIN_ROOT}/scripts/board.mjs" render \
&& echo "MIGRATED: hand-written board -> event log"
fi
Print what it reported: how many events it reconstructed, how many are inferred (ts: null,
because the hand-written board never recorded them), and every note: line — a Cycles column
disagreeing with the ledger is named there, and the migration takes the ledger.
If migrate exits non-zero, do not stop and do not retry it. A board too old to parse (no
Reviewer/Cycles columns, no ledger) has nothing to reconstruct from. Say
LEGACY BOARD: no event log — running the hand-written path and continue; board-doctor is the
backstop for that project exactly as it was before. Neither is an error state: a project with no
board at all is the normal greenfield case, and step 2 creates its log from nothing.
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.
- yesterday First seen · 113 lines · 17 tokens per session scan A c9d1378b03b7
app-plan is a command published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It adds 17 tokens to every session and 1,623 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.
Other commands, from other repositories
factory-report
Linear status report across configured repos — queue depth, triage backlog, ready-to-dispatch, blocked/held.
project
Manage projects: register repos, inspect, configure per-project settings, and remove.
feature
Post a feature to the Features Board on production and write tweets.
commit-all
Group all changes semantically and commit each group separately.
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
android-build
Build Android project with Gradle, fix errors, generate APK/AAB. Invokes android-build-resolver for issues.