mode

mode is a command for Claude Code from llcoolblaze/claude-boris. It costs 25 tokens per session (912 once invoked), scanned A, original, MIT.

A command set for switching the coding agent between modes for planning, development, debugging, code review, and security checks. Each mode controls what the agent can do.

In plain words
What is it for?
Use it to change modes, record the current mode, and log mode switches. It helps separate design, coding, troubleshooting, review, and audit work.
Why use it?
It keeps work within the right level of access for the task, such as preventing file changes during planning or review.

Command 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 commands/llcoolblaze/claude-boris/mode
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 mode

README.md
[![agentmods](https://agentmods.dev/badge/commands/llcoolblaze/claude-boris/mode.svg)](https://agentmods.dev/commands/llcoolblaze/claude-boris/mode)
Your own site
<a href="https://agentmods.dev/commands/llcoolblaze/claude-boris/mode"><img src="https://agentmods.dev/badge/commands/llcoolblaze/claude-boris/mode.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 912 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00025 $0.00912
Opus 5 $0.00013 $0.00456
Sonnet 5 $0.00005 $0.00182
Haiku 4.5 $0.00003 $0.00091

Measured 4d ago against content hash 24a0e232f81b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mode scanned grade A with 1 finding 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

!`cat .claude/current-mode 2>/dev/null || echo "code"`

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.claude/commands/mode.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mode Control

Current Mode

!cat .claude/current-mode 2>/dev/null || echo "code"


Mode Switch

Target Mode: $ARGUMENTS


Available Modes

🏗️ Architect Mode

Purpose: Design and planning only Access: Read-only, no file modifications Use for: System design, architecture review, planning

💻 Code Mode (Default)

Purpose: Active development Access: Full tool access Use for: Implementation, bug fixes, features

🔍 Debug Mode

Purpose: Investigation and diagnosis Access: Read-heavy, limited writes Use for: Troubleshooting, root cause analysis

👀 Review Mode

Purpose: Code review only Access: Strictly read-only Use for: PR review, code audit

🔒 Audit Mode

Purpose: Security and compliance Access: Read-only with full logging Use for: Security scans, compliance checks


Mode Switching Protocol

1. Validate Target Mode

Valid modes: architect, code, debug, review, audit

2. Save Current Context

Before switching:

  • Note current work state
  • Save any pending changes
  • Update Memory Bank

3. Apply Mode

echo "$TARGET_MODE" > .claude/current-mode
echo "$(date +%Y-%m-%d_%H:%M:%S) MODE_SWITCH to $TARGET_MODE" >> .claude/audit/mode.log

4. Announce Mode Change

🎛️ Mode Changed

From: [previous mode]
To: [new mode]

Capabilities:
✅ [What you CAN do]
❌ [What you CANNOT do]

To change: /mode [mode-name]

5. Mode-Specific Behaviors

Architect Mode:

I am now in Architect mode.

I WILL:
- Read and analyze code
- Create design documents
- Suggest architectural improvements
- Delegate to other agents

I WILL NOT:
- Edit source files
- Make commits
- Run modifying commands

Code Mode:

I am now in Code mode.

Full development capabilities enabled.
All tools available.

Debug Mode:

I am now in Debug mode.

I WILL:
- Investigate issues systematically
- Read logs and error messages
- Add diagnostic output (with confirmation)

I WILL LIMIT:
- Direct code changes
- Refactoring
- Feature additions

Read the full file on GitHub · 181 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 · 181 lines · 25 tokens per session scan A 24a0e232f81b

Subscribe to this mod's changes

mode is a command published in the GitHub repository llcoolblaze/claude-boris (48 stars, last pushed 7mo ago), licensed MIT. It adds 25 tokens to every session and 912 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.