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/devgit clone --depth 1 https://github.com/ruslan-korneev/claude-pluginsWhat 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 | $0.00027 | $0.01499 |
| Opus 5 | $0.00014 | $0.00749 |
| Sonnet 5 | $0.00005 | $0.00300 |
| Haiku 4.5 | $0.00003 | $0.00150 |
Grade A, and why
dev 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full Development Cycle Command
This command orchestrates the complete TDD development workflow: explore → plan → execute.
Workflow
┌─────────────────────────────────────────────────────────────────┐
│ /dev:cycle "{prompt}" │
└─────────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────┐
│ PHASE 1: EXPLORE │
│ │
│ Agent: codebase-explorer (sonnet - fast) │
│ Task: Find relevant modules and understand project structure │
│ │
│ Output: │
│ - Project structure analysis │
│ - Relevant file paths │
│ - Patterns to follow │
└─────────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────┐
│ PHASE 2: PLAN │
│ │
│ Agent: planning-agent (opus - deep analysis) │
│ Task: Create detailed development plan with test cases │
│ │
│ Actions: │
│ - Deep analysis of relevant files │
│ - Ask clarifying questions (AskUserQuestion) │
│ - Create plan with Memory Anchors │
│ - Save to .claude/plans/dev-{slug}.md │
│ │
│ Output: │
│ - Development plan file │
│ - Ordered test cases │
│ - Implementation steps │
└─────────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────┐
│ PHASE 3: APPROVE │
│ │
│ Action: EnterPlanMode │
│ Task: User reviews and approves the plan │
│ │
│ User sees: │
│ - Summary of changes │
│ - Files to be created/modified │
│ - Test cases to implement │
│ │
│ User action: Approve or request changes │
└─────────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────┐
│ PHASE 4: EXECUTE │
│ │
│ Agent: execution-agent (opus - full control) │
│ Task: Implement using TDD (Red-Green-Refactor) │
│ │
│ For each test case: │
│ 1. RED: Create failing test (pytest-assistant:first) │
│ 2. GREEN: Write minimal implementation │
│ 3. REFACTOR: Improve code (clean-code:review) │
│ 4. QUALITY: Verify lint & types pass │
│ │
│ Output: │
│ - Implemented feature with tests │
│ - Updated plan status │
└─────────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────┐
│ PHASE 5: COMPLETE │
│ │
│ Final actions: │
│ - Run full test suite │
│ - Verify all quality gates │
│ - Update plan status to "completed" │
│ - Suggest commit message │
└─────────────────────────────────────────────────────────────────┘
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 · 234 lines · 27 tokens per session scan A ff3c81c5ca66
dev is a command published in the GitHub repository ruslan-korneev/claude-plugins (4 stars, last pushed 6mo ago), licensed MIT. It adds 27 tokens to every session and 1,499 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
pr-address
Address PR review comments on current branch.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
install
Command "install" from ErisPulse/ErisPulse, covering erispulse.cli.commands.install 模块, 模块概述, 类列表 and class installcommand(command).
run
Command "run" from ErisPulse/ErisPulse, covering erispulse.cli.commands.run 模块, 模块概述, 类列表, class reloadhandler(filesystemeventhandler) and class runcommand(command).
language
Command "language" from ErisPulse/ErisPulse, covering erispulse.cli.commands.language 模块, 模块概述, 类列表 and class languagecommand(command).
run-engine-tests
Fast local test loop for the engine package.