token-efficiency

token-efficiency is a skill for Claude Code, Codex from ChrisLamDev/hermes-core-skills. It costs 44 tokens per session (1,276 once invoked), scanned A, original, MIT.

A set of practices for keeping the agent's working context focused during long or information-heavy coding sessions.

In plain words
What is it for?
It helps decide what files to read, defer unnecessary reading, summarize information before saving it, and prepare focused context before using other agents.
Why use it?
It helps reduce token use and prevents irrelevant file contents from crowding out information needed for the current task.

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/chrislamdev/hermes-core-skills/token-efficiency
Any agent
npx skills add ChrisLamDev/hermes-core-skills --skill token-efficiency
Clone the repo
git clone --depth 1 https://github.com/ChrisLamDev/hermes-core-skills

Made for: Claude Code, Codex.

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 token-efficiency

README.md
[![agentmods](https://agentmods.dev/badge/skills/chrislamdev/hermes-core-skills/token-efficiency.svg)](https://agentmods.dev/skills/chrislamdev/hermes-core-skills/token-efficiency)
Your own site
<a href="https://agentmods.dev/skills/chrislamdev/hermes-core-skills/token-efficiency"><img src="https://agentmods.dev/badge/skills/chrislamdev/hermes-core-skills/token-efficiency.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,276 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 $0.00044 $0.01276
Opus 5 $0.00022 $0.00638
Sonnet 5 $0.00009 $0.00255
Haiku 4.5 $0.00004 $0.00128

Measured 4d ago against content hash 96569bac999b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

token-efficiency 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.

skills/token-efficiency/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Token Efficiency

Overview

Reduce token consumption by being intentional about what goes into context. Every token costs money and fills the context window. Smart context management can reduce costs by 30-50% without sacrificing quality.

Core principle: Only put in context what's needed for the current task. Everything else is noise.

When to Use

  • Context is approaching the window limit
  • You notice tool outputs are getting large
  • Before dispatching subagents (don't send all context)
  • When working on a long-running session (many turns)
  • When the user mentions cost concerns
  • Before and after context compaction

Techniques

1. Deferred Reading

Don't read files until you need them:

# ❌ Bad: read everything upfront
read_file("src/models/user.py")  # 200 lines
read_file("src/models/product.py")  # 300 lines
read_file("src/models/order.py")  # 250 lines
# → 750 lines in context before you even start

# ✅ Good: read only what you need now
# Start with just the file structure
search_files("*.py", target="files", path="src/models/")
# Read only the file you're about to modify
read_file("src/models/user.py")

2. Summarize Before Saving

Instead of saving raw tool output, summarize:

# ❌ Bad: save raw terminal output
# 200 lines of irrelevant log messages

# ✅ Good: save only the summary
# "Build completed: 45 passed, 0 failed, 3 warnings (all pre-existing)"

3. Use delegate_task for Heavy Lifting

Heavy operations burn token in a separate context, not the main session:

# ❌ Bad: do heavy search in main session
# browser_navigate → browser_snapshot → browser_scroll × 10
# → hundreds of lines of HTML in main context

# ✅ Good: delegate to subagent
delegate_task(goal="Search GitHub trending...", toolsets=['browser'])
# → only the summary enters main context

4. Progressive Disclosure for Skills

Skills should use progressive disclosure (load metadata first, full content only when needed):

# Skill name + 1-line description → Agent decides if relevant
# → Only then load full SKILL.md
# → Only then load reference files

Read the full file on GitHub · 172 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 · 172 lines · 44 tokens per session scan A 96569bac999b

Subscribe to this mod's changes

token-efficiency is a skill published in the GitHub repository ChrisLamDev/hermes-core-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 1,276 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 2026-08-31.