Agent skill

Hermes Cost Audit

by OnlyTerp in OnlyTerp/hermes-optimization-guide

Audit Hermes token spend and propose cuts. An agent skill from OnlyTerp/hermes-optimization-guide.

MITAuto-check passed

Install Hermes Cost Audit

skills CLI
$ npx skills add OnlyTerp/hermes-optimization-guide --skill hermes-cost-audit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install OnlyTerp/hermes-optimization-guide hermes-cost-audit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/OnlyTerp/hermes-optimization-guide.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/hermes-cost-audit .claude/skills/hermes-cost-audit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hermes-cost-audit
GitHub stars
688
Token cost
~985 tokens
SKILL.md length
450 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Audit Hermes token spend and propose cuts. An agent skill from OnlyTerp/hermes-optimization-guide.

  • Works in 6 steps: Measure the fixed prefix that every… → Measure real spend over time → Read the settings that drive cost. auto… → …
  • SKILL.md covers When to Use, Procedure, Verification and Pitfalls
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Hermes Cost Audit is an agent skill from OnlyTerp/hermes-optimization-guide. Audit Hermes token spend and propose cuts.

Its SKILL.md is about 990 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Hermes Agent setup, migration, LightRAG, Telegram, and skill creation guide. The licence is MIT.

Example prompts

  • “/hermes-cost-audit”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Measure the fixed prefix that every model call carries, per surface actually in use
  2. Measure real spend over time
  3. Read the settings that drive cost. auto on an auxiliary task means the main model
  4. Check for these patterns and estimate the saving of each from the step 1 numbers (roughly 4.2–4.5 bytes per token)
  5. Report a table ordered by estimated impact: finding, current value, proposed value, estimated tokens saved per call (or per day), and the…
  6. After approval, apply each change with hermes config set or hermes tools disable, then re-run step 1 and show the before and after.

What it can do on your machine

Read from SKILL.md and the folder at commit f865f8a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hermes Cost Audit loads about 985 tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 450 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~985

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from OnlyTerp/hermes-optimization-guide at commit f865f8a, republished under its MIT licence (© OnlyTerp). 450 words, ~985 tokens.

Download SKILL.mdSave it as .claude/skills/hermes-cost-audit/SKILL.md (or your agent's skills folder).
name
hermes-cost-audit
description
Audit Hermes token spend and propose cuts.
version
1.0.0
author
Terp AI Labs
license
MIT

Hermes Cost Audit

Find where this Hermes install spends tokens and propose the cuts with the best payoff, backed by measurements taken on this machine.

When to Use

  • The user asks why Hermes is expensive, where tokens go, or how to spend less.
  • As a weekly cron job that reports spend and new savings opportunities.

Procedure

Run every command with the terminal tool. Read, measure, and report. Do not change any setting until the user approves the specific change.

  1. Measure the fixed prefix that every model call carries, per surface actually in use:

    bash
    hermes tools --summary                      # which platforms have which toolsets
    hermes prompt-size --json                   # CLI
    hermes prompt-size --platform telegram --json   # repeat for each platform in use

    Record system prompt bytes, skills index bytes, tool schema bytes, and the three largest toolsets per platform.

  2. Measure real spend over time:

    bash
    hermes insights --days 7
    hermes insights --days 30
  3. Read the settings that drive cost. auto on an auxiliary task means the main model:

    bash
    hermes config get model
    hermes config get auxiliary.compression.model
    hermes config get auxiliary.title_generation.model
    hermes config get auxiliary.approval.model
    hermes config get auxiliary.background_review.model
    hermes config get delegation.model
    hermes config get cron.model
    hermes config get agent.disabled_toolsets
    hermes config get prompt_caching.cache_ttl
  4. Check for these patterns and estimate the saving of each from the step 1 numbers (roughly 4.2–4.5 bytes per token):

    PatternProposal
    Auxiliary tasks on auto while the main model is expensiveRoute compression, titles, approvals, and background review to a cheap model. Leave auxiliary.vision unset when the main model can see images: an explicit vision backend makes every image go through a text description.
    A toolset enabled on a platform that never uses it (for example browser or tts on a chat bot)hermes tools disable --platform <platform> <toolset>
    Heavy delegation with delegation.model unsetA cheaper model for subagents
    Several cron jobs with cron.model unsetA cheap default for unpinned cron jobs
    A large project context file where the user usually worksShorten it. Move detail into subdirectory files or skills.
    Long pauses between turns on a Claude model with cache_ttl: 5mConsider 1h (cache writes cost 2x, but pauses stop re-reading at full price)
  5. Report a table ordered by estimated impact: finding, current value, proposed value, estimated tokens saved per call (or per day), and the exact command. Ask which changes to apply.

  6. After approval, apply each change with hermes config set or hermes tools disable, then re-run step 1 and show the before and after.

Show full SKILL.md (106 more words)Show less

Verification

  • hermes prompt-size shows fewer bytes after toolset changes.
  • hermes doctor reports no unresolvable auxiliary routes. An unresolvable route silently falls back to the main model and saves nothing.

Pitfalls

  • image_gen and computer_use are already deferred behind tool search by default. Disabling them does not shrink the prompt.
  • Model switches and tool changes break the prompt cache for the running session. Apply changes, then start a new session.
  • Don't propose capping agent.max_turns as a cost fix. It is unlimited by design, and loop guardrails already stop runaway loops in unattended runs.
  • Don't quote model prices from memory. Point the user at the provider's current pricing page.

© OnlyTerp, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/hermes-cost-audit of OnlyTerp/hermes-optimization-guide.

Open the folder on GitHubat commit f865f8a

Compare with similar skills

Hermes Cost Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hermes Cost Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hermes Cost Audit this skillOnlyTerp/hermes-optimization-guide688—~985Automated safety check: PassMIT
Cost Trackingaffaan-m/ECC276k1 repos~1.3kAutomated safety check: PassMIT
Cloud Cost Optimizationwshobson/agents40k14 repos~1.7kAutomated safety check: PassMIT
Cost Summaryruvnet/ruflo74k—~594Automated safety check: NotesMIT
Cost Conversationruvnet/ruflo74k—~407Automated safety check: NotesMIT
Cost Reportruvnet/ruflo74k—~830Automated safety check: NotesMIT

Similar skills

  • Cost Tracking

    affaan-m/ECC

    Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log.

    276k GitHub starsUsed in 1 repo~1.3k tokens
    AI & LLM EngineeringAuto-check passed
  • Cuts cloud spend across AWS, Azure, GCP and OCI with cost tagging, rightsizing, commitment and spot pricing models, and architecture changes.

    40k GitHub starsUsed in 14 repos~1.7k tokens
    DevOps & CloudAuto-check passed
  • Cost Summary

    ruvnet/ruflo

    Single-shot programmatic dump of all cost data — total spend, per-tier, top session, budget status, federation aggregate.

    74k GitHub stars~594 tokensUpdated today
    Auto-check: notes
  • Cost Conversation

    ruvnet/ruflo

    Per-conversation cost view — list every session in cost-tracking with started-at, message count, top model, and total cost

    74k GitHub stars~407 tokensUpdated today
    AI & LLM EngineeringAuto-check: notes
  • Cost Report

    ruvnet/ruflo

    Generate a cost report showing token usage and USD costs by agent and model

    74k GitHub stars~830 tokensUpdated today
    AI & LLM EngineeringAuto-check: notes
  • Exploring LLM Costs

    PostHog/posthog

    Official

    Investigate LLM spend in PostHog — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost regressions.

    40k GitHub stars~2.9k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from OnlyTerp/hermes-optimization-guide

  • Hermes Offsite Backup

    OnlyTerp/hermes-optimization-guide

    Set up encrypted off-machine Hermes backups. An agent skill from OnlyTerp/hermes-optimization-guide.

    688 GitHub stars~772 tokensUpdated 16 days ago
    Auto-check passed
  • Hermes Health Check

    OnlyTerp/hermes-optimization-guide

    Diagnose a Hermes install and report fixes. An agent skill from OnlyTerp/hermes-optimization-guide.

    688 GitHub stars~936 tokensUpdated 16 days ago
    Auto-check passed
  • Hermes Security Review

    OnlyTerp/hermes-optimization-guide

    Review Hermes settings for security risks. An agent skill from OnlyTerp/hermes-optimization-guide.

    688 GitHub stars~1.1k tokensUpdated 16 days ago
    Auto-check: notes

Questions about Hermes Cost Audit

What does Hermes Cost Audit do?

Audit Hermes token spend and propose cuts. An agent skill from OnlyTerp/hermes-optimization-guide. Hermes Cost Audit is an agent skill from OnlyTerp/hermes-optimization-guide. Audit Hermes token spend and propose cuts.

How do I install Hermes Cost Audit in Claude Code?

Run `npx skills add OnlyTerp/hermes-optimization-guide --skill hermes-cost-audit -a claude-code`. Or copy the skill folder (skills/hermes-cost-audit in OnlyTerp/hermes-optimization-guide) into .claude/skills/hermes-cost-audit in your project. Claude Code loads it when a task matches its description.

How do I install Hermes Cost Audit in Codex?

Run `npx skills add OnlyTerp/hermes-optimization-guide --skill hermes-cost-audit -a codex`. Or copy the skill folder (skills/hermes-cost-audit in OnlyTerp/hermes-optimization-guide) into .agents/skills/hermes-cost-audit in your project. Codex loads it when a task matches its description.

Can I use Hermes Cost Audit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OnlyTerp/hermes-optimization-guide --skill hermes-cost-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hermes-cost-audit, .gemini/skills/hermes-cost-audit, .github/skills/hermes-cost-audit and .opencode/skills/hermes-cost-audit in your project.

What does Hermes Cost Audit need to run?

SKILL.md names no scripts, command-line tools or credentials: Hermes Cost Audit is instructions for the agent only.

Does Hermes Cost Audit access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hermes Cost Audit safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hermes Cost Audit use?

Hermes Cost Audit is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hermes Cost Audit use?

About 985 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Hermes Cost Audit?

Skills that share tags, products or a category with Hermes Cost Audit: Cost Tracking (affaan-m/ECC, 276k stars), Cloud Cost Optimization (wshobson/agents, 40k stars), Cost Summary (ruvnet/ruflo, 74k stars) and Cost Conversation (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hermes Cost Audit?

OnlyTerp (a GitHub user) maintains it in OnlyTerp/hermes-optimization-guide, which has 688 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on September 24, 2026.

Source: OnlyTerp/hermes-optimization-guide on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.