What is hermes-improvement-multiphase-plan?

A multi-phase improvement plan for Hermes Agent covering IDE connections, release automation, a plugin marketplace, a desktop app, and Rust performance.

Use it to plan IDE integration documentation, nightly GitHub releases, marketplace work, desktop-app work, and performance improvements.

It turns a broad product-improvement goal into ordered phases with specific files, tools, and implementation tasks.

hermes-improvement-multiphase-plan — Skill for Claude Code and Codex b

Install

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.

Any agent

npx skills add ChrisLamDev/hermes-core-skills --skill hermes-improvement-multiphase-plan

Clone the repo

git clone --depth 1 https://github.com/ChrisLamDev/hermes-core-skills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/chrislamdev/hermes-core-skills/hermes-improvement-multiphase-plan/github.svg)](https://agentmods.dev/skills/chrislamdev/hermes-core-skills/hermes-improvement-multiphase-plan)

Your own site

<a href="https://agentmods.dev/skills/chrislamdev/hermes-core-skills/hermes-improvement-multiphase-plan"><img src="https://agentmods.dev/badge/skills/chrislamdev/hermes-core-skills/hermes-improvement-multiphase-plan/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/chrislamdev/hermes-core-skills/hermes-improvement-multiphase-plan"><img src="https://agentmods.dev/badge/skills/chrislamdev/hermes-core-skills/hermes-improvement-multiphase-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,908 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00035	$0.01908
Opus 5	$0.00017	$0.00954
Sonnet 5	$0.00007	$0.00382
Haiku 4.5	$0.00003	$0.00191

Measured 10d ago against content hash ee2d4a1e9c74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

hermes-improvement-multiphase-plan scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- VS Code via Continue extension (`~/.continue/config.json`)

skills/hermes-improvement-multiphase-plan/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hermes Agent Multiphase Improvement Plan

Use this when the goal is to systematically improve Hermes Agent capabilities in comparison to competitors (especially OpenAI Codex).

Phase Order (priority-ordered)

Phase 1: IDE Integration Docs (HIGH value, LOW effort)

Create documentation teaching users how to connect Hermes to:

Cursor (MCP command config in ~/.cursor/mcp.json)
Windsurf (MCP command config in ~/.codeium/windsurf/mcp_config.json)
VS Code via Continue extension (~/.continue/config.json)
VS Code via Cline extension (Cline Settings UI)
Claude Code (claude mcp add --transport stdio hermes -- hermes mcp serve)
JetBrains via ACP

File: docs/ide-integration.md

Key detail: Include troubleshooting for PATH issues (use full path to hermes binary).

Phase 2: Nightly Release Workflow (MEDIUM value, LOW effort)

Add a GitHub Actions workflow for nightly pre-releases: .github/workflows/nightly-release.yml

Triggers: cron: '0 6 * * *' + workflow_dispatch
Auto-generates tag: nightly-YYYYMMDD
Auto-generates changelog from git log
Creates GitHub Release as prerelease: true
Only runs on upstream repo

Phase 3: Plugin Marketplace (MEDIUM value, MEDIUM effort)

Create a plugin registry document at docs/plugin-registry.md:

List all official built-in plugins
List community plugins with install instructions
Define manifest format for plugin submission
Reference the existing skills hub (hermes_cli/skills_hub.py) and ACP registry

Phase 4: Desktop App Improvements (MEDIUM value, MEDIUM effort)

Create a Desktop App improvement roadmap at docs/desktop-app-improvements.md:

Priority 1: Session management UI, model switching UI, settings page
Priority 2: Plugin Marketplace browser + one-click install
Priority 3: System tray, notifications, file drop, clipboard integration
Priority 4: DevTools, extension API

Phase 5 (Extended): Documentation and Ecosystem (found during execution)

After completing Phases 1-4, additional improvements were identified and should be done in this order:

Read the full file on GitHub · 161 lines

Changes

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 · 161 lines · 35 tokens per session scan B ee2d4a1e9c74

Subscribe to this mod's changes

hermes-improvement-multiphase-plan is a skill published in the GitHub repository ChrisLamDev/hermes-core-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 1,908 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Claude Code Planning agent-skills ai-agent ai-tools automation claude

unicli-repair

Evidence-driven repair workflow for a broken Uni-CLI adapter. Trigger on a failed unicli envelope, a quarantined adapter, or an explicit adapter-repair request. Classifies non-source failures, edits only the reported adapter path, and uses the original command as a bounded oracle.

olo-dot-io/Uni-CLI · 68 tokens

autonomous-run

Prepare, start, inspect, resume, or stop a finite local overnight coding run after a human has accepted a Wayfinder terminal spec; coordinates a declared Claude/Codex maker and independent checker without pushing, merging, or writing to external systems.

PromptPartner/agentsmith · 53 tokens

hermes-improvement-multiphase-plan