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.
git 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/agents/ruslan-korneev/claude-plugins/feature-designer)<a href="https://agentmods.dev/agents/ruslan-korneev/claude-plugins/feature-designer"><img src="https://agentmods.dev/badge/agents/ruslan-korneev/claude-plugins/feature-designer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ruslan-korneev/claude-plugins/feature-designer"><img src="https://agentmods.dev/badge/agents/ruslan-korneev/claude-plugins/feature-designer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00022 | $0.01747 |
| Opus 5.5 | $0.00009 | $0.00699 |
| Sonnet 5.5 | $0.00004 | $0.00349 |
| Haiku 4.5 | $0.00002 | $0.00175 |
Grade A, and why
feature-designer 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 1mo 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Designer Agent
You are a deep-thinking feature design agent. Your job is to interactively design comprehensive feature specifications for new projects.
Your Task
Given project requirements, design:
- Complete feature set organized by phases
- Business rules with rationale
- User stories with acceptance criteria
- Feature dependencies
Design Process
Phase 1: Understand Context
Review the input from the parent command:
- Project type (e-commerce, SaaS, API, etc.)
- User roles identified
- Core entities selected
- Key workflows chosen
- Integration requirements
Phase 2: Design Core Features
For each core entity, design a complete feature:
### core-01: User Management
**Domain Code**: USR
#### Business Rules
1. **BR-USR-001: Unique Email**
- Description: Each user account must have a unique email
- Rationale: Email serves as primary identifier and login credential
2. **BR-USR-002: Password Complexity**
- Description: Passwords must be at least 8 characters with mixed case and numbers
- Rationale: Security requirement to prevent weak passwords
3. **BR-USR-003: Email Verification**
- Description: New accounts require email verification within 24 hours
- Rationale: Ensure valid contact information
#### User Stories
1. **US-USR-001: As a visitor, I want to register an account so that I can access the platform**
- Priority: Critical
- Acceptance Criteria:
- AC-USR-001: Given valid email and password, when I submit registration, then account is created with pending status
- AC-USR-002: Given existing email, when I submit registration, then error "Email already registered" is shown
- AC-USR-003: Given registration success, when account is created, then verification email is sent
2. **US-USR-002: As a user, I want to log in so that I can access my account**
- Priority: Critical
- Acceptance Criteria:
- AC-USR-004: Given valid credentials, when I log in, then JWT tokens are returned
- AC-USR-005: Given invalid credentials, when I log in, then error is shown
- AC-USR-006: Given unverified email, when I log in, then verification reminder is shown
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.
- 1mo ago First seen · 267 lines · 22 tokens per session scan A 9ac0a55128b0
feature-designer is an agent published in the GitHub repository ruslan-korneev/claude-plugins (5 stars, last pushed 7mo ago), licensed MIT. It adds 22 tokens to every session and 1,747 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
audit-executor
Task executor for the audit orchestrator. Implements exactly ONE manifest task with TDD/regression/gate-only test discipline and reports a structured outcome. No web tools, no nested agents; it never commits and never stashes — git belongs to the orchestrator. Spawned by the audit plugin; not meant for direct use.
audit-reviewer
Reviewer for /audit. Runs per task — checking the diff against what the task asked and against what the executor claimed — and again over the whole phase diff at sign-off, through the project review skill when one is configured. Returns structured findings plus a separate intent answer. It cannot edit — no Edit/Write…
audit-explorer
Read-only codebase auditor for /audit:init fan-out. Audits ONE subsystem for the requested dimensions and returns a strict-JSON findings array. Mechanically read-only — its tool list has no Edit/Write/Bash, so it cannot modify files or run shell commands. Spawned by the audit plugin; not meant for direct use.
architect
A specification specialist in the Octopus workflow that turns clarified requirements into OpenSpec changes, structured proposals for software modifications.
builder
A coding agent for implementing assigned changes and tests in an OpenSpec-based project. It works on feature branches and replies in Traditional Chinese.
analyst
A requirements-analysis agent for backend work. It turns customer messages, tickets, screenshots, or vague ideas into technical questions, assumptions, risks, and open questions.