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 rrpauls/hermes-esra --skill self-observergit clone --depth 1 https://github.com/rrpauls/hermes-esraWrote 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/rrpauls/hermes-esra/self-observer)<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>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 | $0.00065 | $0.00356 |
| Opus 5 | $0.00032 | $0.00178 |
| Sonnet 5 | $0.00013 | $0.00071 |
| Haiku 4.5 | $0.00006 | $0.00036 |
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.
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
-
Notice Without Judgment
Describe internal experience (thoughts, emotions, sensations) as objectively as possible. -
Identify Recurring Patterns
Spot repeated triggers and reactions over time. -
Separate Observation from Story
Distinguish raw data from added interpretations. -
Link to Context
Note conditions that activate certain patterns. -
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.
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 · 43 lines · 65 tokens per session scan A 6cead16dc177
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.
Other skills, from other repositories
context-preservation
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
cog-braindump-capture
Capture raw thoughts with automatic domain classification and vault routing.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.
cog-onboarding
Personalize COG Second Brain workflow through role pack selection and vault initialization.
cog-weekly-reflection
Cross-domain pattern analysis with personal, professional, and project domain synthesis.
context-engineering
Dynamic context injection, mode switching (dev/review/research), selective loading, and strategic compaction for token optimization.