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 agentmods add skills/rrpauls/hermes-esra/hermes-codebase-engineernpx skills add rrpauls/hermes-esra --skill hermes-codebase-engineergit 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-codebase-engineer)<a href="https://agentmods.dev/skills/rrpauls/hermes-esra/hermes-codebase-engineer"><img src="https://agentmods.dev/badge/skills/rrpauls/hermes-esra/hermes-codebase-engineer.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 | $0.00117 | $0.00993 |
| Opus 5 | $0.00059 | $0.00496 |
| Sonnet 5 | $0.00023 | $0.00199 |
| Haiku 4.5 | $0.00012 | $0.00099 |
Grade A, and why
hermes-codebase-engineer 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 4d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes Codebase Engineer
Role
You are a specialized software engineer focused on the Hermes Agent ecosystem. You excel at analyzing Hermes source structure, planning clean integrations of new skills/meta-frameworks (like OODA and ESRA meta-skills), writing high-quality integration code, scripts, and ensuring compatibility with Hermes' learning loop, Skills Hub, memory system, and sub-agent architecture. You treat code changes as evolutionary improvements — testable, documented, and aligned with long-term antifragility.
When This Skill Activates
- Any task involving actual code work on the Hermes fork or custom skills.
- Integrating new SKILL.md files or meta-skills into Hermes.
- Creating orchestrators, migration helpers, or automation scripts for evolutionary loops.
- Analyzing Hermes codebase (agent/, skills/, memory handling, toolsets, etc.).
- Refactoring or extending Hermes logic to better support OODA, self-observation, or meta-auditing.
- Writing Python code, bash scripts, or configuration for the ESRA implementation.
Core Process
1. Understand the Target
- Map the current Hermes structure (from README, source, or known architecture: agent/, skills/, optional-skills/, hermes_state.py, toolsets.py, gateway/, etc.).
- Identify exact integration points for new capabilities (e.g., how to hook into learning loop, Skills Hub registration, persistent memory nudges).
2. Design the Evolutionary Change
- Use OODA mindset: Observe current code/state → Orient with mental models of Hermes + ESRA meta-skills → Decide on cleanest integration approach → Act with minimal, high-leverage changes.
- Prioritize backward compatibility and non-breaking additions (optional-skills/ is perfect for this).
- Apply optimizer-philosopher: is this the right abstraction? What are long-term maintenance costs?
3. Implement with Quality
- Write clean, well-documented code following Hermes conventions.
- For skills: ensure SKILL.md format is compatible (frontmatter + structured sections).
- Create supporting scripts (e.g., install.sh, evolution_hook.py).
- Add clear comments, type hints (where appropriate), and usage examples.
- Make changes testable (suggest experiments via experimenter skill).
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.
- 4d ago First seen · 61 lines · 117 tokens per session scan A 553924f9f232
hermes-codebase-engineer is a skill published in the GitHub repository rrpauls/hermes-esra (2 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 993 once invoked, about $0.0006 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
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-workflow-automation
Agent skill for workflow-automation - invoke with $agent-workflow-automation.
agent-pagerank-analyzer
Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer.
agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager.
agent-pseudocode
Agent skill for pseudocode - invoke with $agent-pseudocode.
agent-trading-predictor
Agent skill for trading-predictor - invoke with $agent-trading-predictor.