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/bentleypark/claude-code-mobile-spine/featgit clone --depth 1 https://github.com/bentleypark/claude-code-mobile-spineWrote 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/bentleypark/claude-code-mobile-spine/feat)<a href="https://agentmods.dev/commands/bentleypark/claude-code-mobile-spine/feat"><img src="https://agentmods.dev/badge/commands/bentleypark/claude-code-mobile-spine/feat.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.07935 |
| Opus 5 | $0.00026 | $0.03967 |
| Sonnet 5 | $0.00010 | $0.01587 |
| Haiku 4.5 | $0.00005 | $0.00793 |
Grade A, and why
feat 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 4d 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 — 480 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mobile-spine:feat — New feature kickoff interview
Run a 4-item interview, then invoke pm-agent automatically. The main session asks the user the 4 questions in order, collects answers, and constructs the pm-agent prompt. Three early checks can divert before the case interview: a requirement too large for one PR cycle (Item 1b — epic) routes to pm-agent's phased decomposition; a feature already built on one platform but not the other (Item 1c — parity) routes to the cross-platform parity flow; a change that alters no backend endpoint (Item 1d — client-only) skips the spec pre-checks entirely. All three skip Items 2–4 — parity skips them entirely (it's a near-zero-input path: the reference implementation is the spec), epic defers them to per-phase authoring, and client-only settles them by classification (no spec to source; the existing screen is the design).
The workspace's /feat is a thin stub that delegates here — both invocations end up running this same command.
Workspace prerequisite
This command operates on a scaffolded mobile-spine workspace. Before running the interview, verify .claude/mobile-spine.config.yaml exists in the current directory — if not, abort:
"[/feat] No .claude/mobile-spine.config.yaml found in the current working directory. This doesn't look like a mobile-spine workspace. Run /mobile-spine:init for a fresh setup, or follow SETUP.md §0 to migrate from v1.x."
Then apply the same schema check pm-agent runs (pm-agent.md Configuration → §Config schema versioning): a mobileSpineSchemaVersion higher than the plugin's warns once and proceeds; lower, absent, or non-integer aborts here. Same reason as the file check — pm-agent would abort at invocation anyway, and the interview would already be spent.
(pm-agent reads the same config at invocation; the checks here are a fast-fail so the user doesn't sit through the 4-item interview before discovering the workspace isn't set up, or is at a schema this plugin cannot read.)
User argument: $ARGUMENTS
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.
- 4d ago First seen · 480 lines · 51 tokens per session scan A d35cd3e87122
feat is a command published in the GitHub repository bentleypark/claude-code-mobile-spine (1 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 7,935 once invoked, about $0.0003 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
audit
Scan a codebase for existing observability instrumentation and identify gaps.
instrument
Generate a comprehensive instrumentation plan for a mobile codebase.
mobile-verify
Run automated verification loops with pass@k metrics for mobile testing. Executes tests multiple times to detect flakiness.
feature-learn
View and manage patterns learned from feature builds. Shows extracted instincts, confidence scores, and feature completeness history.
feature-plan
Plan a mobile feature with architecture decisions, file breakdown, dependency analysis, and test strategy. Produces a structured plan document reviewed by an architecture agent.
platform-info
Detect project type (Android/iOS/KMP), list platforms, show platform info, and delegate to appropriate commands.