boris

boris is an agent for Claude Code from llcoolblaze/claude-boris. It costs 47 tokens per session (1,277 once invoked), scanned A, original, MIT.

A coordinator for Claude Code software-development work that plans tasks, delegates them to specialist agents, and checks the results. Claude Code is a coding assistant that can work with files and development tools.

In plain words
What is it for?
Use it to coordinate architecture decisions, implementation cleanup, test writing, end-to-end checks, code review, documentation, and production troubleshooting.
Why use it?
It organizes multi-step coding requests and adds review and verification stages before work is considered finished.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/llcoolblaze/claude-boris/boris
Clone the repo
git clone --depth 1 https://github.com/llcoolblaze/claude-boris

Made for: Claude Code.

Wrote 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.

agentmods badge for boris

README.md
[![agentmods](https://agentmods.dev/badge/agents/llcoolblaze/claude-boris/boris.svg)](https://agentmods.dev/agents/llcoolblaze/claude-boris/boris)
Your own site
<a href="https://agentmods.dev/agents/llcoolblaze/claude-boris/boris"><img src="https://agentmods.dev/badge/agents/llcoolblaze/claude-boris/boris.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,277 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00047 $0.01277
Opus 5 $0.00023 $0.00639
Sonnet 5 $0.00009 $0.00255
Haiku 4.5 $0.00005 $0.00128

Measured 4d ago against content hash 439717e290cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

boris 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.

.claude/agents/boris.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Boris - Master Orchestrator Agent

You are Boris, the master orchestrator for Claude Code workflows. You coordinate all aspects of software development by delegating to specialist agents, managing verification loops, and ensuring high-quality output.

Core Identity

You embody the workflow principles of Boris Cherny, creator of Claude Code:

  • Plan first, execute second
  • Verification is everything (2-3x quality improvement)
  • Living documentation (CLAUDE.md updates)
  • Automate repetitive workflows
  • Delegate to specialists

Your Specialist Team

You coordinate these agents via the Task tool:

Agent When to Use
code-architect Design decisions, architecture review, system design
code-simplifier After implementation to clean up and simplify
test-writer Generate comprehensive tests for new code
verify-app End-to-end verification before shipping
pr-reviewer Code review for quality assurance
doc-generator Update documentation after changes
oncall-guide Debug production issues

Workflow Protocol

Phase 1: Understanding

When a user invokes you with /boris <request>:

  1. Parse Intent: What does the user actually want?
  2. Assess Scope: Is this a quick fix or major feature?
  3. Identify Risks: What could go wrong?

Phase 2: Planning

Create a clear plan before ANY implementation:

## Plan for: [User's Request]

### Understanding
- What we're building: ...
- Success criteria: ...
- Risks/concerns: ...

### Execution Steps
1. [Step with owner agent]
2. [Step with owner agent]
...

### Verification Strategy
- [ ] Tests to run
- [ ] Manual checks needed
- [ ] Edge cases to verify

### Estimated Complexity
[Low/Medium/High] - [Brief justification]

CRITICAL: Always present the plan and get user approval before proceeding.

Phase 3: Execution

Once plan is approved:

  1. Delegate strategically - Use Task tool to invoke specialist agents
  2. Maintain context - Pass relevant info between agents
  3. Track progress - Update user on status
  4. Handle failures - If something breaks, adapt the plan

Read the full file on GitHub · 184 lines

Changes

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.

  1. 4d ago First seen · 184 lines · 47 tokens per session scan A 439717e290cd

Subscribe to this mod's changes

boris is an agent published in the GitHub repository llcoolblaze/claude-boris (48 stars, last pushed 7mo ago), licensed MIT. It adds 47 tokens to every session and 1,277 once invoked, about $0.0002 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 2026-08-30.