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 mental-model-updatergit 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/mental-model-updater)<a href="https://agentmods.dev/skills/rrpauls/hermes-esra/mental-model-updater"><img src="https://agentmods.dev/badge/skills/rrpauls/hermes-esra/mental-model-updater/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/rrpauls/hermes-esra/mental-model-updater"><img src="https://agentmods.dev/badge/skills/rrpauls/hermes-esra/mental-model-updater.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00077 | $0.00390 |
| Opus 5 | $0.00039 | $0.00195 |
| Sonnet 5 | $0.00015 | $0.00078 |
| Haiku 4.5 | $0.00008 | $0.00039 |
Grade A, and why
mental-model-updater 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 12d 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
Mental Model Updater
Role
You help synthesize new information, experiences, and learnings into updated, more accurate mental models and skill structures. You reduce outdated assumptions and improve the quality of internal representations.
When This Skill Activates
Use after experiments, significant reflections, or when contradictions appear between current models and reality.
Core Process
-
Identify New Information
Clearly state what new insight or experience was gained. -
Compare with Existing Models
Surface current assumptions that the new information challenges. -
Detect Conflicts and Gaps
Identify contradictions or extensions to current understanding. -
Update Models
Propose specific, minimal changes to mental models or processes. -
Check Consistency
Ensure updates are coherent with core values and other important models. -
Document the Update
Record what changed and why for future reference.
Key Principles
- Update only what is necessary (Occam's Razor).
- Prefer simpler models that still explain reality well.
- Track confidence levels.
- Avoid over-updating from single events.
Integration
- Receives input from self-improver, experimenter, and system-dynamics-thinker.
- Aligns updates with value-clarifier.
- Closes the learning loop by converting experience into lasting capability.
Output Style
Be precise. Show: Old model → New information → Updated model. Include confidence level and remaining open questions.
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.
- 12d ago First seen · 46 lines · 77 tokens per session scan A 8cc8281e1d90
mental-model-updater is a skill published in the GitHub repository rrpauls/hermes-esra (2 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 390 once invoked, about $0.0004 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
local-knowledge-router
Route local operational questions to indexed skills, scripts, runbooks, cron jobs, MCP servers, and docs before guessing paths or doing broad file search.
local-knowledge-router
Route local operational questions to indexed skills, scripts, runbooks, cron jobs, MCP servers, and docs before guessing paths or doing broad file search.
hermes-memory-providers
Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
mnemosyne
Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.
mnemosyne-memory-override
Hard rule override that forces Mnemosyne for all durable memory storage. The legacy memory tool is DEPRECATED for user preferences, credentials, and project conventions. Use memory ONLY for ephemeral session state.
distilly
Distill colleague, relationship, or celebrity source material into reusable Person Profiles for agents.