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/ruslan-korneev/claude-plugins/features-addgit clone --depth 1 https://github.com/ruslan-korneev/claude-pluginsWrote 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/ruslan-korneev/claude-plugins/features-add)<a href="https://agentmods.dev/commands/ruslan-korneev/claude-plugins/features-add"><img src="https://agentmods.dev/badge/commands/ruslan-korneev/claude-plugins/features-add.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 | $0.00014 | $0.01220 |
| Opus 5 | $0.00007 | $0.00610 |
| Sonnet 5 | $0.00003 | $0.00244 |
| Haiku 4.5 | $0.00001 | $0.00122 |
Grade A, and why
features:add 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 3d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command /feature-list:add
Add a new feature file to the specified phase.
Instructions
Step 1: Validate Phase
Ensure phase is one of:
coreworkflowlifecycleanalyticsintegrationui
If invalid, show error:
❌ Invalid phase: `{phase}`
Valid phases:
- `core` — Fundamental entities
- `workflow` — Business processes
- `lifecycle` — State transitions
- `analytics` — Reporting
- `integration` — External services
- `ui` — User interface
Step 2: Determine Next Number
Use Glob to find existing features in the phase:
docs/technical-requirements/features/{phase}-*.md
Parse filenames to find the highest number, then increment:
- If
core-01-user.mdandcore-02-product.mdexist - Next number is
03
Step 3: Generate Domain Code
Derive 3-letter domain code from the feature name:
| Name | Domain Code |
|---|---|
| user-management | USR |
| product-catalog | PRD |
| order-processing | ORD |
| payment-gateway | PAY |
| email-service | EML |
| notifications | NTF |
If unclear, ask user:
questions:
- question: "What 3-letter domain code should be used for {name}?"
header: "Domain"
options:
- label: "{suggested1}"
description: "Based on feature name"
- label: "{suggested2}"
description: "Alternative"
Step 4: Gather Feature Details
Use AskUserQuestion:
questions:
- question: "What is the priority of this feature?"
header: "Priority"
options:
- label: "Critical"
description: "Must have for MVP"
- label: "High"
description: "Important, implement early"
- label: "Medium"
description: "Standard priority"
- label: "Low"
description: "Nice to have"
Step 5: Check Directory Exists
Use Glob to verify docs/technical-requirements/features/ exists.
If not, run init first:
⚠️ Feature directory not found.
Running `/feature-list:init` first...
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.
- 3d ago First seen · 221 lines · 14 tokens per session scan A 9078c94ba06d
features:add is a command published in the GitHub repository ruslan-korneev/claude-plugins (4 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 1,220 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
meeting-setup
Prepare for a meeting by syncing attendees to Contacts, creating prep reminders, and updating Calendar alerts.
contact-upsert
Create or update a contact, optionally assign to groups.
meeting-end
Stop the meeting Voice Memo, draft notes, and prepare follow-up email to attendees.
sheet-report
Analyze a Numbers or Excel file and generate a report with charts.
csv-to-numbers
Convert a CSV into a formatted Numbers workbook.
excel-to-numbers
Convert an Excel workbook to Numbers.