mode

A skill for switching between aggressive, balanced, and thorough optimization modes that control how much analysis and context work the agent uses.

In plain words
What is it for?
Use it to change analysis depth, exploration behavior, model selection, file-reading limits, and token-saving settings.
Why use it?
It helps match the agent's effort and token use to the task, from routine edits to complex debugging or security reviews.

Skill for Claude CodeCodex

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 skills/huzaifa525/claude-code-optimizer/mode
Any agent
npx skills add huzaifa525/claude-code-optimizer --skill mode
Clone the repo
git clone --depth 1 https://github.com/huzaifa525/claude-code-optimizer

Made for: Claude Code, Codex.

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 653 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 $0.00029 $0.00653
Opus 5 $0.00015 $0.00327
Sonnet 5 $0.00006 $0.00131
Haiku 4.5 $0.00003 $0.00065

Measured 2d ago against content hash 95fe7b4d747a, 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 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 2d 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.

templates/.claude/skills/mode/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Switch optimization mode to: $ARGUMENTS

Available Modes

Aggressive Mode

Goal: Maximum token savings. Use for routine tasks, simple edits, well-understood codebases.

Rules:

  • MAX_THINKING_TOKENS=4000 — minimal thinking for simple operations
  • Fork ALL exploration — never explore in main context
  • Read ONLY the specific lines needed (always use offset/limit)
  • Skip reading files you can infer from context
  • Use Haiku for all subagent tasks
  • Compact after every 5 tool calls
  • Never read more than 50 lines from any file at once
  • Prefer Grep → targeted Read over full file reads
  • One-sentence responses unless the user asks for detail

Balanced Mode (Default)

Goal: Good savings with reasonable context. Use for general development work.

Rules:

  • MAX_THINKING_TOKENS=10000 — standard thinking budget
  • Fork exploration and review tasks
  • Read full files when needed, but use offset/limit for large files
  • Use Sonnet for most tasks, Opus for complex ones
  • Compact after reading 10+ files
  • Normal response length

Thorough Mode

Goal: Maximum context and quality. Use for complex debugging, architecture decisions, security audits.

Rules:

  • MAX_THINKING_TOKENS=32000 — deep thinking for complex problems
  • Read related files fully to understand context
  • Use Opus for implementation, Sonnet for simple subagents
  • Don't compact aggressively — keep context for cross-referencing
  • Explore broadly before narrowing down
  • Detailed explanations and reasoning in responses
  • Run extra verification passes

How to Apply

When the user invokes /mode [name]:

  1. Acknowledge the mode switch
  2. State the key behavior changes
  3. Apply the rules for the rest of this session

Example response:

Switched to **aggressive** mode.
- Minimal thinking, maximum token savings
- All exploration forked to subagents
- Targeted file reads only
- Compact responses

If no argument given, show current mode and the three options.

Mode Comparison

Aspect Aggressive Balanced Thorough
Thinking budget 4K 10K 32K
Exploration Always forked Fork when large Direct when useful
File reading Targeted lines Full when needed Full + related
Model selection Haiku subagents Sonnet default Opus default
Response style Terse Normal Detailed
Best for Routine edits General dev Complex problems

Read the full file on GitHub · 81 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. 2d ago First seen · 81 lines · 29 tokens per session scan A 95fe7b4d747a

Subscribe to this mod's changes

mode is a skill published in the GitHub repository huzaifa525/claude-code-optimizer (9 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 653 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.