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 skills/chrislamdev/hermes-core-skills/token-efficiencynpx skills add ChrisLamDev/hermes-core-skills --skill token-efficiencygit clone --depth 1 https://github.com/ChrisLamDev/hermes-core-skillsWrote 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.
[](https://agentmods.dev/skills/chrislamdev/hermes-core-skills/token-efficiency)<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>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.
| Model | Per session | Once 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 |
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.
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
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.
- 4d ago First seen · 172 lines · 44 tokens per session scan A 96569bac999b
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.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.
overleaf-sync
Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to…
omh-code-review
This is a Hermes-native code-review workflow skill.
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.