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/kaeawc/auto-mobile/device-lifecyclegit clone --depth 1 https://github.com/kaeawc/auto-mobileWhat 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 | $0.00037 | $0.00507 |
| Opus 5 | $0.00018 | $0.00253 |
| Sonnet 5 | $0.00007 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
device-lifecycle 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.
What it actually says
Load and follow the device-session-lifecycle skill
(skills/device-session-lifecycle/SKILL.md) — it is the source of truth for
the identifiers, invariants, recurring bug classes, weak-spot map, and test
discipline. Its references/history.md catalogs every past lifecycle
issue/PR by era and bug class.
Input
$ARGUMENTS is one of:
- An issue number — read it with
gh issue view, classify the symptom against the skill's bug classes, check the history catalog for a prior instance, then hunt per the skill's procedure (§4). - A symptom description — same, starting from the identifier classification step (§1): which of the four identifiers is involved?
audit <area>(e.g.audit shutdown,audit registry retire paths) — sweep the named area's weak spots (§6) for violations of the invariants (§2), following the audit style of Era 4 (coded findings, one issue per confirmed defect).- Empty — ask what to hunt, offering the open threads listed at the end of the skill as candidates.
Rules
- Before diagnosing, rule out the documented environment artifacts (skill §4.2): daemon-restart transport wedge, multi-worktree daemon churn, DisconnectMonitor auto-restart, stale dist behind a fresh version string.
- Ground every claim in adb/simctl/process-table/daemon-log evidence, never
a tool's
successflag. - A fix is not done until a unit test forces the exact interleaving via the injected seams (FakeTimer/FakeIdGenerator/fakes), and — for anything touching pool runtime identity or streaming — a live-emulator or stream-subscriber check has run (skill §7 blind spots).
- File issues / open PRs per repo conventions (
skills/ship-issue,skills/push-pr) when the user asks for fixes to land.
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.
- 2d ago First seen · 42 lines · 0 tokens per session scan A b6e116a24b15
device-lifecycle is a command published in the GitHub repository kaeawc/auto-mobile (45 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 507 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.