Agent skill

Hermes Insights

Generate insights about your Claude Code usage — what topics you work on most, common patterns, productivity trends.

MITAuto-check passed

Install Hermes Insights

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill hermes-insights -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC hermes-insights --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/hermes-insights .claude/skills/hermes-insights && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "hermes-insights" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/hermes-insights into .claude/skills/hermes-insights/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-insights", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/hermes-insights

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill hermes-insights -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC hermes-insights --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/hermes-insights .agents/skills/hermes-insights && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "hermes-insights" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/hermes-insights into .agents/skills/hermes-insights/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-insights", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill hermes-insights -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC hermes-insights --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/hermes-insights .cursor/skills/hermes-insights && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "hermes-insights" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/hermes-insights into .cursor/skills/hermes-insights/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-insights", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/AlexAI-MCP/hermes-CCC.git --path skills/hermes-insights

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill hermes-insights -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC hermes-insights --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/hermes-insights .gemini/skills/hermes-insights && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "hermes-insights" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/hermes-insights into .gemini/skills/hermes-insights/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-insights", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC hermes-insights

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill hermes-insights -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/hermes-insights .github/skills/hermes-insights && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "hermes-insights" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/hermes-insights into .github/skills/hermes-insights/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-insights", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill hermes-insights -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC hermes-insights --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/hermes-insights .opencode/skills/hermes-insights && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "hermes-insights" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/hermes-insights into .opencode/skills/hermes-insights/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-insights", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: hermes-insights
GitHub stars: 135
Token cost: ~1.8k tokens
SKILL.md length: 578 words
Files: 1
Skills in repo: 44
Repo updated: Apr 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Generate insights about your Claude Code usage — what topics you work on most, common patterns, productivity trends.

Works in 5 steps: Memory Files — Topic and Theme Extraction → Skills Used — Skill Utilization → Project Types and Domains → …
SKILL.md covers Invocation, Subcommands, Data Sources and What Claude… and Full Output Structure, plus 3 more sections
Calls fastapi, vercel and claude

What it does

Hermes Insights is an agent skill from AlexAI-MCP/hermes-CCC. Generate insights about your Claude Code usage — what topics you work on most, common patterns, productivity trends.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Hermes Agent ported to Claude Code Channel — 46 native skills, no OAuth, no external process. The licence is MIT.

Example prompts

“/hermes-insights”

Requirements

Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Memory Files — Topic and Theme Extraction
Skills Used — Skill Utilization
Project Types and Domains
Conversation Patterns
Data Hygiene and Confidence Rules

What it can do on your machine

Read from SKILL.md and the folder at commit 8107e89. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- fastapi
- vercel
- claude
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use vercel, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hermes Insights loads about 1.8k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 578 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~33
When it runs · the whole SKILL.md, loaded when a task matches: ~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from AlexAI-MCP/hermes-CCC at commit 8107e89, republished under its MIT licence (© AlexAI-MCP). 578 words, ~1,751 tokens.

Download SKILL.mdSave it as .claude/skills/hermes-insights/SKILL.md (or your agent's skills folder).

name: hermes-insights
description: Generate insights about your Claude Code usage — what topics you work on most, common patterns, productivity trends.
version: 1.0.0
author: hermes-CCC (ported from Hermes Agent by NousResearch)
license: MIT

hermes-insights

Analyze your Claude Code usage patterns across sessions and produce a structured insight report: what topics you work on most, which skills you use, what types of projects dominate your workflow, and where your productivity is strongest.

Invocation

/hermes-insights
/hermes-insights --days <N>

Subcommands

`/hermes-insights` — Full Analysis

Analyzes all available memory files and session history with no time constraint.

`/hermes-insights --days <N>` — Time-Bounded Analysis

Restricts analysis to session files created in the last N days.

How Claude filters by date:

bash

find ~/.claude/projects/*/memory/session_*.md \
     -mtime -<N> -type f

Data Sources and What Claude Analyzes

1. Memory Files — Topic and Theme Extraction

bash

ls ~/.claude/projects/*/memory/session_*.md

For each session file, Claude reads the decisions, facts_learned, artifacts_created, and open_issues sections and extracts noun phrases as topic signals. Topics are then counted and ranked by frequency across all sessions.

Output: Top 10 topics, each with session count and a representative example decision or fact.

2. Skills Used — Skill Utilization

bash

ls ~/.claude/skills/
ls ~/.claude/projects/*/skills/ 2>/dev/null

Claude counts which skill directories exist and cross-references session memory files for any /skill-name invocation patterns mentioned in the decisions or facts_learned fields.

Output: Skill utilization table (skill name, invocation count estimate, last used date).

3. Project Types and Domains

Claude reads each session file's project: field (from the hermes-compress YAML) and groups sessions by project slug. It then infers the domain from artifact paths and topic keywords (e.g., .py artifacts + "Neo4j" keywords → "graph database / Python backend").

Output: Project breakdown table (project, session count, primary domain, last active date).

4. Conversation Patterns

Claude counts per-session: number of decisions made, artifacts created, problems solved, and open issues left unresolved. These become productivity metrics.

Output: Per-week averages for decisions, artifacts, and resolution rate (problems solved / open issues ratio).

5. Data Hygiene and Confidence Rules

Skip any session file that is missing the expected hermes-compress YAML block and record how many files were excluded.
Normalize topic strings by lowercasing, trimming punctuation, and folding obvious singular/plural variants before counting.
Prefer explicit evidence from decisions and artifacts_created over weak inference from prose when assigning project domains.
Mark a skill as inferred if the file only mentions the skill name indirectly and no /skill-name invocation is present.
Downgrade trend claims to low confidence when fewer than 5 sessions match the selected date range.
Report no sessions matched the filter instead of fabricating empty charts when --days <N> returns zero files.
Treat duplicate session paths with identical timestamps as one observation so repeated syncs do not inflate counts.
Fall back to unknown project when the project: field is absent and artifact paths do not provide a clear slug.
Separate unresolved carry-over work from newly opened issues so the resolution rate is not overstated.

Show full SKILL.md (152 more words)Show less

Full Output Structure

## Claude Code Usage Insights
Generated: 2026-04-07 | Sessions analyzed: 23 | Date range: 2026-02-14 – 2026-04-07

### Top Topics
| Rank | Topic              | Sessions | Example |
|------|--------------------|----------|---------|
| 1    | Neo4j / graph DB   | 14       | "Use Neo4j as primary ontology store" |
| 2    | FastAPI / Python   | 11       | "REST endpoints for /query and /ingest" |
| 3    | Vercel deployment  | 7        | "Deploy to Vercel with vercel link --repo" |
| 4    | OpenCrab ontology  | 6        | "Fallback to neo4j when opencrab returns 0" |
| 5    | Discord integration| 4        | "Reply via plugin_discord_discord reply tool" |

### Skill Utilization
| Skill             | Est. Invocations | Last Used  |
|-------------------|-----------------|------------|
| hermes-compress   | 18              | 2026-04-07 |
| hermes-memory     | 12              | 2026-04-05 |
| hermes-search     | 9               | 2026-04-06 |
| hermes-persona    | 5               | 2026-04-03 |
| honcho            | 3               | 2026-03-28 |

### Project Breakdown
| Project       | Sessions | Domain                  | Last Active |
|---------------|----------|-------------------------|-------------|
| ontology      | 14       | Graph DB / Python API   | 2026-04-07 |
| AlexAI        | 6        | LLM product / strategy  | 2026-04-02 |
| hermes-CCC    | 3        | Claude Code skills      | 2026-04-07 |

### Productivity Trends (weekly averages)
- Decisions per session: 4.2
- Artifacts created per session: 2.8
- Problems solved per session: 1.9
- Resolution rate: 68% (open issues closed within 2 sessions)

### Recommendations
- **Automate Neo4j setup:** It appears in 61% of sessions. Consider a project template.
- **Increase hermes-compress frequency:** 5 sessions have no memory file (no compress run).
- **hermes-persona unused in recent sessions:** Last used 4 days ago — may boost focus in coder mode.

### Key Takeaway
You are most productive in graph database and Python API work, averaging 2.8 artifacts per session, with a 68% issue resolution rate.

How Claude Gathers the Data

List all session memory files: ls -t ~/.claude/projects/*/memory/session_*.md
For each file: read the YAML block, extract fields, count keywords.
Aggregate counts using simple frequency tallies in working memory.
Format and output the insight report.

Claude does not write any files during /hermes-insights. The command is read-only.

Relationship to Hermes `/insights` Command

This skill mirrors the /insights command in Hermes Agent (NousResearch), which produces usage analytics from the SQLite session store. In hermes-CCC, the equivalent data source is the Markdown session memory files written by hermes-compress. The output categories (topics, skill utilization, productivity trends, recommendations) match the Hermes insights contract.

Notes

Accuracy improves with more hermes-compress runs. Sessions without a memory file are invisible to this analysis.
/hermes-insights works best after at least 5 sessions of memory accumulation.
Pair with honcho update to keep the user profile current after reviewing insights.

Files

Just SKILL.md in skills/hermes-insights of AlexAI-MCP/hermes-CCC.

Open the folder on GitHubat commit 8107e89

Compare with similar skills

Hermes Insights next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hermes Insights compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Hermes Insights this skillAlexAI-MCP/hermes-CCC	135	—	~1.8k	Automated safety check: Pass	MIT	6 mo ago
Hermes Importsaffaan-m/ECC	276k	—	~324	Automated safety check: Pass	MIT	yesterday
Hermes Importsaffaan-m/ECC	277k	1 repos	~752	Automated safety check: Pass	MIT	today
Inspecting Hermes Desktop DomNousResearch/hermes-agent	253k	1 repos	~1.6k	Automated safety check: Pass	MIT	today
Hermes Tweetwshobson/agents	40k	—	~1.4k	Automated safety check: Pass	MIT	6 days ago
Hermes Agent Skill AuthoringNousResearch/hermes-agent	252k	—	~3.6k	Automated safety check: Pass	MIT	yesterday

Similar skills

Hermes Imports
affaan-m/ECC
将本地 Hermes 操作员工作流转换为经过清理的 ECC 技能和发布包工件。在准备将 Hermes 工作流用于公共 ECC 重用而不泄露私有工作区状态、凭据或仅本地路径时使用。
276k GitHub stars~324 tokensUpdated yesterday
Auto-check passed
Hermes Imports
affaan-m/ECC
Convert local Hermes operator workflows into sanitized ECC skills and release-pack artifacts.
277k GitHub starsUsed in 1 repo~752 tokens
Auto-check passed
Inspecting Hermes Desktop Dom
NousResearch/hermes-agent
Read the live Hermes desktop DOM/CSS over CDP. An agent skill from NousResearch/hermes-agent.
253k GitHub starsUsed in 1 repo~1.6k tokens
Frontend & DesignAuto-check passed
Hermes Tweet
wshobson/agents
Install and operate Hermes Tweet, a Hermes Agent plugin for X/Twitter research, timeline reading, tweet analysis, and approval-gated private or state-changing operations.
40k GitHub stars~1.4k tokensUpdated 6 days ago
Writing & ContentAuto-check passed
Hermes Agent Skill Authoring
NousResearch/hermes-agent
Author in-repo SKILL.md files: frontmatter and structure. An agent skill from NousResearch/hermes-agent.
252k GitHub stars~3.6k tokensUpdated yesterday
Agent WorkflowsAuto-check passed
Formatting Insight Axes
PostHog/posthog
Official
Pick the right y-axis unit when creating or updating an insight via posthog:insight-create or posthog:insight-update — both TrendsQuery (trendsFilter.aggregationAxisFormat) and SQL insights…
40k GitHub stars~2.1k tokensUpdated yesterday
DatabasesAuto-check passed

Questions about Hermes Insights

What does Hermes Insights do?

Generate insights about your Claude Code usage — what topics you work on most, common patterns, productivity trends. Hermes Insights is an agent skill from AlexAI-MCP/hermes-CCC. Generate insights about your Claude Code usage — what topics you work on most, common patterns, productivity trends.

How do I install Hermes Insights in Claude Code?

Run `npx skills add AlexAI-MCP/hermes-CCC --skill hermes-insights -a claude-code`. Or copy the skill folder (skills/hermes-insights in AlexAI-MCP/hermes-CCC) into .claude/skills/hermes-insights in your project. Claude Code loads it when a task matches its description.

How do I install Hermes Insights in Codex?

Run `npx skills add AlexAI-MCP/hermes-CCC --skill hermes-insights -a codex`. Or copy the skill folder (skills/hermes-insights in AlexAI-MCP/hermes-CCC) into .agents/skills/hermes-insights in your project. Codex loads it when a task matches its description.

Can I use Hermes Insights in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AlexAI-MCP/hermes-CCC --skill hermes-insights -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hermes-insights, .gemini/skills/hermes-insights, .github/skills/hermes-insights and .opencode/skills/hermes-insights in your project.

What does Hermes Insights need to run?

Going by SKILL.md and its folder, Hermes Insights needs the command-line tools its instructions call (fastapi, vercel and claude). Our summary lists: Python 3.

Does Hermes Insights access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hermes Insights safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hermes Insights use?

Hermes Insights is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hermes Insights use?

About 1.8k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Hermes Insights?

Skills that share tags, products or a category with Hermes Insights: Hermes Imports (affaan-m/ECC, 276k stars), Hermes Imports (affaan-m/ECC, 277k stars), Inspecting Hermes Desktop Dom (NousResearch/hermes-agent, 253k stars) and Hermes Tweet (wshobson/agents, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hermes Insights?

AlexAI-MCP (a GitHub user) maintains it in AlexAI-MCP/hermes-CCC, which has 135 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on April 8, 2026.

Source: AlexAI-MCP/hermes-CCC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Hermes Insights

Facts

At a glance

What it does

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

hermes-insights

Invocation

Subcommands

/hermes-insights — Full Analysis

/hermes-insights --days <N> — Time-Bounded Analysis

Data Sources and What Claude Analyzes

1. Memory Files — Topic and Theme Extraction

2. Skills Used — Skill Utilization

3. Project Types and Domains

4. Conversation Patterns

5. Data Hygiene and Confidence Rules

Full Output Structure

How Claude Gathers the Data

Relationship to Hermes /insights Command

Notes

Files

Compare with similar skills

Similar skills

More from AlexAI-MCP/hermes-CCC

Questions about Hermes Insights

`/hermes-insights` — Full Analysis

`/hermes-insights --days <N>` — Time-Bounded Analysis

Relationship to Hermes `/insights` Command