hermes-self-evaluation

hermes-self-evaluation is a skill for Claude Code, Codex from AtlasOmnia/hermes-custom-pack. It costs 69 tokens per session (2,567 once invoked), scanned A, a copy of hermes-self-evaluation, MIT.

A review process for examining Hermes Agent's own sessions, settings, skills, costs, and usage patterns. Hermes Agent is the system being evaluated.

In plain words
What is it for?
Use it to audit Hermes performance, find automation opportunities, review spending or usage, and validate proposed system improvements.
Why use it?
It helps separate observed problems from their likely causes before recommending changes. This reduces the risk of optimizing based on incomplete or misleading signals.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; positional $N argument.

Good fit Use it to audit Hermes performance, find automation opportunities, review spending or usage, and validate proposed system improvements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/atlasomnia/hermes-custom-pack/hermes-self-evaluation
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.

Any agent
npx skills add AtlasOmnia/hermes-custom-pack --skill hermes-self-evaluation
Clone the repo
git clone --depth 1 https://github.com/AtlasOmnia/hermes-custom-pack

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 hermes-self-evaluation

README.md
[![agentmods](https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/hermes-self-evaluation/github.svg)](https://agentmods.dev/skills/atlasomnia/hermes-custom-pack/hermes-self-evaluation)
Your own site
<a href="https://agentmods.dev/skills/atlasomnia/hermes-custom-pack/hermes-self-evaluation"><img src="https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/hermes-self-evaluation/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.

agentmods 80×15 button for hermes-self-evaluation

Your own site · 80×15
<a href="https://agentmods.dev/skills/atlasomnia/hermes-custom-pack/hermes-self-evaluation"><img src="https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/hermes-self-evaluation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,567 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 5.1 $0.00069 $0.02567
Opus 5 $0.00034 $0.01283
Sonnet 5 $0.00014 $0.00513
Haiku 4.5 $0.00007 $0.00257

Measured 9d ago against content hash f3eb1f6600da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

hermes-self-evaluation 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 9d 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.

Origin

This is a copy

100% identical to hermes-self-evaluation — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/hermes-self-evaluation/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hermes Self-Evaluation

Use this skill when the user asks to audit, review, or optimize Hermes's own performance — analyzing session data, skills, configuration, costs, and usage patterns to identify improvements, automation opportunities, and system optimizations.

Don't use for: skill content quality grading (use skill-auditor instead), one-off task analysis, or session artifact indexing after a work session (use session-artifact-indexing).

Overview

The core workflow: gather live evidence about Hermes's state and history → validate each finding against the subsystem's actual semantics and control surface → either produce a direct evidence-backed review or compose a structured analyst prompt for an independent model → verify recommendations before implementation.

External models are useful anomaly detectors and critics, but they are not automatically reliable root-cause analysts. Separate the observed symptom, supported interpretation, confirmed producer/root cause, and proposed change. Before acting on any self-check finding,

When to Use

Triggers:

  • "How can we improve Hermes?"
  • "Analyze my sessions and tell me what to optimize"
  • "I want to have another model evaluate X"
  • "Where do sessions/skills live so I can analyze them?"
  • "Do an audit of the system"
  • "What's the token cost breakdown?"

Workflow

Fast Path: Evaluate a Single Runaway Session

When the user names a specific session and says it was “working” too long, hit a tool-call guardrail, ignored “stop,” or needs the problem evaluated, do not build a broad system-audit prompt first. Diagnose the named session directly.

Use for the exact SQL/Python checks. Minimum evidence to collect:

  1. Session metadata from ~/.hermes/state.db: source, title, model, start/end times, message count, tool-call count, token totals, end reason.
  2. Role counts and top tool counts.
  3. User-message timeline and non-tool assistant replies, especially around compaction/restore and the latest steering instruction.
  4. Repeated assistant tool_call IDs. Exact repeated call_ids are a strong sign of stale tool-call replay after context compaction or gateway restore.
  5. Log markers for the session ID: max_iterations_reached, Preflight compression, Pre-API compression, gateway shutdown, Operation interrupted, tool-call guardrail, idempotent_no_progress, and transport retry loops.
  6. If relevant, check whether any live process from the runaway task is still active before saying it is safe to abandon.

Read the full file on GitHub · 208 lines

Files

What ships with it

3 files 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.

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. 9d ago First seen · 208 lines · 69 tokens per session scan A f3eb1f6600da

Subscribe to this mod's changes

hermes-self-evaluation is a skill published in the GitHub repository AtlasOmnia/hermes-custom-pack (56 stars, last pushed 25d ago), licensed MIT. It adds 69 tokens to every session and 2,567 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to hermes-self-evaluation, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories