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/ahmed3elshaer/everything-claude-code-mobile/feature-learngit clone --depth 1 https://github.com/ahmed3elshaer/everything-claude-code-mobileWrote 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/ahmed3elshaer/everything-claude-code-mobile/feature-learn)<a href="https://agentmods.dev/commands/ahmed3elshaer/everything-claude-code-mobile/feature-learn"><img src="https://agentmods.dev/badge/commands/ahmed3elshaer/everything-claude-code-mobile/feature-learn.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 | $0.00021 | $0.00886 |
| Opus 5 | $0.00010 | $0.00443 |
| Sonnet 5 | $0.00004 | $0.00177 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
feature-learn 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Learn Command
View patterns learned from feature builds. Displays instincts captured during Phase 7 (Learning), confidence scores, and feature completeness history over time.
Usage
# Show all learned feature patterns
/feature-learn
# Show patterns for a specific feature
/feature-learn auth
# Export learned patterns for sharing across projects
/feature-learn --export
Flags
| Flag | Values | Description |
|---|---|---|
| (none) | Show all learned patterns and completeness scores | |
<name> |
Feature name | Show learning details for a specific feature |
--export |
Export all learned patterns to .omc/exports/feature-instincts.json |
Output
All Features Summary
Feature Learning Summary
========================
Features Analyzed: 3
Total Patterns Captured: 28
High Confidence Instincts (>= 0.7): 12
Feature Completeness Scores:
auth .................. 100% (12 patterns, 2026-03-28)
payments .............. 85% (10 patterns, 2026-03-27)
profile ............... 60% (6 patterns, 2026-03-26)
Top Instincts:
sealed-interface-state ....... 0.9 (mvi-architecture)
compose-state-hoisting ....... 0.8 (jetpack-compose)
repository-interface ......... 0.8 (clean-architecture)
koin-module-def .............. 0.7 (koin-patterns)
Specific Feature Detail
Feature: auth
Platform: android
Learned: 2026-03-28T10:20:00Z
Completeness: 100%
Composite Patterns:
feature-clean-architecture ... PRESENT (25%)
feature-mvi-complete ......... PRESENT (25%)
feature-di-complete .......... PRESENT (15%)
feature-test-coverage ........ PRESENT (20%)
feature-navigation-wired ..... PRESENT (15%)
Individual Patterns Detected (12):
- sealed-interface-state (mvi-architecture)
- sealed-interface-intent (mvi-architecture)
- sealed-interface-side-effect (mvi-architecture)
- mvi-intent-handling (mvi-architecture)
- coroutine-structured (coroutines-patterns)
- compose-state-hoisting (jetpack-compose)
- repository-interface (clean-architecture)
- repository-impl (clean-architecture)
- usecase-class (clean-architecture)
- koin-module-def (koin-patterns)
- koin-viewmodel-injection (koin-patterns)
- compose-navigation-route (navigation-patterns)
Build Metrics:
Build Iterations: 2
Quality Findings: 0 critical, 1 medium
pass@k: 0.96
Coverage: 84%
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 · 116 lines · 21 tokens per session scan A 931ecbf07315
feature-learn is a command published in the GitHub repository ahmed3elshaer/everything-claude-code-mobile (65 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 886 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 2026-09-03.
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.
feat
Kick off tasks creation for a new feature (4-item interview before invoking pm-agent; an epic-sized requirement routes to phased decomposition, a feature already built on one platform routes to cross-platform parity, a change that touches no endpoint routes to client-only).
status
Project health dashboard - shows environment status and suggests improvements.
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.