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 skills add moonlight-lupin/agent-skills --skill input-token-overheadsgit clone --depth 1 https://github.com/moonlight-lupin/agent-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/moonlight-lupin/agent-skills/input-token-overheads)<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/input-token-overheads"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/input-token-overheads/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/input-token-overheads"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/input-token-overheads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 194 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 5.1 | $0.00027 | $0.02732 |
| Opus 5 | $0.00014 | $0.01366 |
| Sonnet 5 | $0.00005 | $0.00546 |
| Haiku 4.5 | $0.00003 | $0.00273 |
Grade A, and why
input-token-overheads 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 11d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Input Token Overheads
Audit every source of per-turn input token cost on a Hermes Agent instance. Measure each, rank by cost, act on the top consumers.
When to Use
- User says "token overhead", "context too large", "why is input so expensive"
- Model output quality degrades from context dilution
- Cost optimization — fewer input tokens per turn means lower API spend
- After adding skills, plugins, or tools — verify the overhead delta
The Overhead Map
Every turn, Hermes injects these blocks into the system prompt before the user's message:
| Block | When loaded | Cost model |
|---|---|---|
| Skill descriptions | Every turn (skill-retrieval top-K) | ~200 chars per description, K per turn |
| Memory (personal notes) | Every turn | Static, grows with usage |
| User profile | Every turn | Static, grows as preferences accumulate |
| Memory provider context | Every turn (if memory plugin active) | Dynamic, 5 memories recalled by default |
| Tool schemas (direct) | Every turn | Full JSON schema per enabled tool |
| Deferred tool catalog | Every turn (if configured) | Name + description only |
| Mandatory skills | Every turn (if configured) | Full SKILL.md body |
| Platform formatting rules | Every turn | Fixed, platform-specific |
| Behavioral rules | Every turn | Fixed system prompt text |
| Full skill body | On-demand (skill_view) | Only when a skill is loaded |
| Compression summary | After threshold | Replaces older messages with a summary |
On-demand (not per-turn): full SKILL.md via skill_view, deferred tool schemas via tool_describe, reference files via skill_view(file_path=...).
Health Ratio
The health metric is overhead ratio: overhead tokens divided by the model's context window. The absolute number matters for cost; the ratio matters for quality.
| Ratio | Rating | Notes |
|---|---|---|
| < 5% | Excellent | Most of the window available for conversation |
| 5-15% | Healthy | Normal for a capable agent with tools, skills, memory |
| 15-25% | Acceptable | Approaching the limit. Consider trimming. |
| > 25% | Unhealthy | Eats conversation capacity. Cost and quality risk. |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 205 lines · 27 tokens per session scan A ea8bc3ee9128
input-token-overheads is a skill published in the GitHub repository moonlight-lupin/agent-skills (60 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 2,732 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 2026-08-30.
Other skills, from other repositories
SoloFlow
A meta-skill that silently watches your workflows and automatically generates reusable Hermes skills from them.
hermes-tweet
Use Xquik in Hermes Agent for public X research, monitoring, thread summaries, creator discovery & approved actions. Not affiliated with X Corp. Use when the user requests X data or a named action. Trigger with "search X", "monitor X", "post tweet", or "X trends".
image
Create or optimize marketing images, social graphics, product mockups, banners, cover art, listing visuals, brand assets, image prompts, WebP files, and OG images.
video
Plan and produce video with available AI tools or programmatic frameworks. Use for video prompts, avatars, explainers, demos, templates, pipelines, and generation.
content-analysis
Analyze articles, documents, videos, podcasts, and transcripts for arguments, evidence, themes, assumptions, contradictions, insights, and unanswered questions.
content-research-writer
Research, outline, draft, cite, and revise articles, reports, tutorials, newsletters, and case studies with traceable sources and preserved voice.