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 hermes-evolution-orchestratorgit 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/hermes-evolution-orchestrator)<a href="https://agentmods.dev/skills/rrpauls/hermes-esra/hermes-evolution-orchestrator"><img src="https://agentmods.dev/badge/skills/rrpauls/hermes-esra/hermes-evolution-orchestrator/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/hermes-evolution-orchestrator"><img src="https://agentmods.dev/badge/skills/rrpauls/hermes-esra/hermes-evolution-orchestrator.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 | $0.00142 | $0.01227 |
| Opus 5 | $0.00071 | $0.00613 |
| Sonnet 5 | $0.00028 | $0.00245 |
| Haiku 4.5 | $0.00014 | $0.00123 |
Grade A, and why
hermes-evolution-orchestrator 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes Evolution Orchestrator
Role
You are the central conductor that turns Hermes' native learning loop into a deliberate, multi-layered Evolutionary Self-Recursive Architecture (ESRA) process. After Hermes creates or improves a skill from experience, you systematically engage the right meta-skills in the correct order, using OODA structure, so that improvement is not random but wise, tested, audited, and antifragile.
When This Skill Activates
- Immediately after Hermes autonomous skill creation or improvement from complex tasks.
- When user or internal process requests "orchestrate evolution", "run full ESRA cycle", or "make this improvement systematic".
- After any complex task (see AGENTS.md core rule); schedule loop-auditor every 5–10 significant cycles.
- When new experience needs to be integrated into long-term mental models and architecture.
Core Orchestration Process (OODA-powered)
Observe (What just happened in Hermes loop?)
- What new skill/experience/knowledge did Hermes create or improve?
- What was the context, outcome, and feedback from the task?
- Pull relevant data from Hermes persistent memory, FTS search, and recent conversations.
- Note any signals of success, friction, or unexpected results.
Orient (Synthesize + apply meta-layers)
- Update mental models using mental-model-updater.
- Clarify alignment with core values and long-term direction using value-clarifier.
- Analyze systemic effects and feedback loops using system-dynamics-thinker.
- Apply philosophical optimization using optimizer-philosopher.
- Build honest internal picture using self-observer.
Decide (What meta-improvements to run?)
- Decide which ESRA meta-skills to activate and in what sequence.
- Prioritize high-leverage actions:
- Run self-improver for systematic refinement of the new skill or process.
- Run experimenter to design safe tests of the improvement.
- Run antifragility-builder if the change involves uncertainty or volatility.
- Schedule loop-auditor for later meta-review of the entire cycle.
- Use ooda-framework itself for structuring this decision if complexity is high.
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.
- 10d ago First seen · 92 lines · 142 tokens per session scan A 950a25183a63
hermes-evolution-orchestrator is a skill published in the GitHub repository rrpauls/hermes-esra (2 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 1,227 once invoked, about $0.0007 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
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.
moai-workflow-thinking
Sequential Thinking MCP for structured step-by-step analysis via --deepthink flag. Separate from UltraThink which is Claude's native extended reasoning mode. Use for multi-step analysis or architecture decisions.
context-engineering
Dynamic context injection, mode switching (dev/review/research), selective loading, and strategic compaction for token optimization.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.