hermes-agent-dissect
Skill1 starsChanged 7 months agoMITView on GitHub
Navigate and extract reusable design patterns from the Hermes Agent source code for application in our project. It covers ten subsystems: bootstrap/CLI, conversation engine, prompt/context, tool system, gateway/messaging, skills, terminal backends, memory/persistence, RL training, and integrations (ACP/MCP/plugins).
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ascii-renderingSkill
- claude-code-dissectSkill
- codex-collabSkill
- market-dataSkill
- mogu-visualSkill
- particle-effectsSkill
- podcast-to-mdSkill
- twitter-scraperSkill
- web-searchSkill
- xiaohongshu-to-markdownSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 29
Locate the source root: search the project for hermes-agent/run_agent.py using Glob.
- Distinctive: line 51
If the topic spans multiple areas, read the primary reference first, then follow its Neighbors section to related files.
- Distinctive: line 53
If no topic matches, grep the source root for relevant keywords before giving up.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Hermes Agent Source Dissection
Setup
The Hermes Agent source tree lives at hermes-agent/ in the project root.
Auto-discover the source root by searching for hermes-agent/run_agent.py using Glob.
The directory containing it is SOURCE_ROOT. All file paths in the reference files are relative to this SOURCE_ROOT.
How to use this skill
- Locate the source root: search the project for
hermes-agent/run_agent.pyusing Glob. The parent directory ofrun_agent.pyisSOURCE_ROOT. - Identify the topic from the user's request
- Read the matching reference file from
references/below - Read the actual source files listed in the reference — prepend
SOURCE_ROOT/to each path - Present your findings using the output format at the bottom
Routing Table
| Topic | Reference File | Covers |
| Startup, CLI, config, profiles, auth, credentials | references/bootstrap.md | Entry points, config.yaml, credential pool, constants, setup wizard |
| Conversation loop, tool calling, streaming, multi-turn | references/engine.md | AIAgent main loop, tool dispatch, parallelization, budget, Honcho |
| System prompt, SOUL.md, context compression, caching | references/context.md | Prompt assembly, context files, compressor, cache strategy, tokens |
| Tool definition, registry, toolsets, execution, dispatch | references/tools.md | Tool interface, registry singleton, toolset composition, async bridge |
| Gateway, platforms, messaging, Telegram, Discord, Feishu | references/gateway.md | GatewayRunner, 14 platform adapters, sessions, delivery, interrupts |
| Skills, SOUL.md parsing, skill hub, security scanning | references/skills.md | Progressive disclosure, hub lifecycle, guard patterns, slash commands |
| Terminal execution, Docker, SSH, Modal, local, sandbox | references/terminals.md | Backend abstraction, persistent shell, approval, dangerous commands |
| Memory, sessions, persistence, checkpoints, todo | references/memory.md | Memory tool, session storage, Honcho integration, checkpoint system |
| RL training, environments, benchmarks, trajectory | references/training.md | Atropos base env, OPD, web research, batch runner, compression |
| ACP, MCP, plugins, delegation, model routing | references/integrations.md | ACP server, MCP tool bridge, plugin system, subagent delegation |
If the topic spans multiple areas, read the primary reference first, then follow its Neighbors section to related files.
If no topic matches, grep the source root for relevant keywords before giving up.
Output Format
Structure your response like this:
Pattern: one-line name Why it exists: 2-3 sentences on the problem it solves Data flow:
ASCII diagram showing runtime flowKey code (from the source, simplified):
# The core abstraction, stripped to essentialsFiles read: list with line numbers for critical sections Design tradeoffs: what was gained, what was sacrificed How to adapt: what to keep, what to change for our project
Architecture Overview
For orientation, here's how the 10 subsystems connect:
User Input (CLI / TUI / Gateway / ACP)
|
[bootstrap] -> config.yaml, credentials, profile selection
|
[engine] -> AIAgent loop: message -> LLM -> stream -> tool calls -> continue/end
| |
[context] -> prompt assembly [tools] -> registry -> dispatch -> async bridge
| | | |
[memory] <- compression [skills] <--- [terminals] <- backends
| | |
+-- persistence [training] <- RL environments, benchmarks
|
[integrations] -> ACP, MCP, plugins, delegation
|
[gateway] -> 14 platforms, sessions, deliveryEach reference file contains: architecture knowledge, key abstractions, reading order, file table with line counts, and neighbor cross-references.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.