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-analysisgit 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-analysis)<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/input-token-analysis"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/input-token-analysis/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-analysis"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/input-token-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00014 | $0.02567 |
| Opus 5 | $0.00007 | $0.01283 |
| Sonnet 5 | $0.00003 | $0.00513 |
| Haiku 4.5 | $0.00001 | $0.00257 |
Grade A, and why
input-token-analysis 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 8d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Input Token Analysis
Explain aggregate input token consumption. Answer three questions with numbers: where did the tokens go, which consumers dominate, what config or prompt change reduces them. Distinct from input-token-overheads, which audits per-turn system-prompt blocks. This skill audits total volume across sessions, cron fires, and tool traffic.
When to Use
- Monthly/weekly input token bill is large and unexplained (e.g. "2.4B tokens in 30 days")
- After applying token-saving changes — measure the delta against a baseline
- A cron job is suspected of runaway token use
For per-turn context-window health, use input-token-overheads. For API billing disputes, use the provider's usage dashboard — local telemetry cannot see provider-side caching.
Quick Start
Run the audit script (read-only, pure stdlib):
python3 ~/.hermes/skills/agent-ops/input-token-analysis/scripts/audit.py --days 30
# other profiles: --db ~/.hermes/profiles/<name>/state.db
# custom cron ledger: --cron-audit /path/to/usage_audit.jsonl --jobs /path/to/jobs.json
The script prints: totals by task/model/provider, cache-read and cache-write columns, weighted per-call averages (long sessions and short-session floor), top sessions, cron offenders, active-only tool-result volume with the tool-share percentage, and oversized-result counts. Everything is derived from real DB rows — never estimate by hand when the script can measure.
Pre-Check Discipline
Verify before advising. Advice formed from memory is not acceptable.
- Config keys and current values — read the live value first:
hermes config get <key>. Never state a current value from memory or assume the default is in force. - Defaults and mechanisms — confirm a key exists and what it does against the installed build (
hermes_cli/config_defaults.py) or the Hermes docs. If the installed build and docs disagree, say so. - Provider behavior — do not assume a provider reports cache fields, honors a pricing tier, or counts tokens a certain way. Probe it or check its current docs before claiming.
- Unverifiable claims — mark them UNVERIFIED in the report. A labeled unknown beats a confident guess.
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.
- 8d ago First seen · 121 lines · 14 tokens per session scan A 4df92ee0c269
input-token-analysis is a skill published in the GitHub repository moonlight-lupin/agent-skills (64 stars, last pushed 5d ago), licensed MIT. It adds 14 tokens to every session and 2,567 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 2026-09-04.
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-research-writer
Research, outline, draft, cite, and revise articles, reports, tutorials, newsletters, and case studies with traceable sources and preserved voice.
content-analysis
Analyze articles, documents, videos, podcasts, and transcripts for arguments, evidence, themes, assumptions, contradictions, insights, and unanswered questions.