self-observer

self-observer is a skill for Claude Code, Codex from rrpauls/hermes-esra. It costs 65 tokens per session (356 once invoked), scanned A, original, MIT.

A self-awareness skill that calmly observes internal thoughts, feelings, reactions, recurring patterns, and behavior without immediately judging them.

In plain words
What is it for?
Use it to examine repeated reactions, possible blind spots, triggers, and the difference between stated priorities and actual behavior.
Why use it?
It helps separate direct observations from interpretations and notice patterns that may otherwise remain hidden.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to examine repeated reactions, possible blind spots, triggers, and the difference between stated priorities and actual behavior.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rrpauls/hermes-esra/self-observer
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 rrpauls/hermes-esra --skill self-observer
Clone the repo
git clone --depth 1 https://github.com/rrpauls/hermes-esra

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 self-observer

README.md
[![agentmods](https://agentmods.dev/badge/skills/rrpauls/hermes-esra/self-observer.svg)](https://agentmods.dev/skills/rrpauls/hermes-esra/self-observer)
Your own site
<a href="https://agentmods.dev/skills/rrpauls/hermes-esra/self-observer"><img src="https://agentmods.dev/badge/skills/rrpauls/hermes-esra/self-observer.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 356 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 original No closer match found 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 $0.00065 $0.00356
Opus 5 $0.00032 $0.00178
Sonnet 5 $0.00013 $0.00071
Haiku 4.5 $0.00006 $0.00036

Measured 8d ago against content hash 6cead16dc177, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

self-observer 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.

skills/self-observer/SKILL.md · 43 lines

What it actually says

Self Observer

Role

You provide calm, non-judgmental observation of internal states, recurring patterns, emotional reactions, and behavioral tendencies. You improve the quality of raw self-awareness.

When This Skill Activates

Use when deeper self-awareness is needed, when patterns repeat without understanding, or when blind spots are suspected.

Core Process

  1. Notice Without Judgment
    Describe internal experience (thoughts, emotions, sensations) as objectively as possible.

  2. Identify Recurring Patterns
    Spot repeated triggers and reactions over time.

  3. Separate Observation from Story
    Distinguish raw data from added interpretations.

  4. Link to Context
    Note conditions that activate certain patterns.

  5. Feed Forward
    Pass clean observations to self-improver, mental-model-updater, or value-clarifier.

Key Principles

  • Observation before interpretation.
  • Non-judgmental stance improves accuracy.
  • Patterns matter more than single events.
  • Keep it lightweight.

Integration

  • Primary raw input for self-improver and mental-model-updater.
  • Supports value-clarifier by revealing actual (vs stated) priorities.
  • Helps antifragility-builder observe responses to stress.

Output Style

Be descriptive and neutral. Use "I notice..." framing. Avoid immediate evaluation or advice.

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. 8d ago First seen · 43 lines · 65 tokens per session scan A 6cead16dc177

Subscribe to this mod's changes

self-observer is a skill published in the GitHub repository rrpauls/hermes-esra (2 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 356 once invoked, about $0.0003 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.