mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-07-31 19:16:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

fix(skills): sync coding-agent CLI skills to current flags/packages

Browse source 
Four coding-agent CLI skills drifted from their live CLIs. Verified against live --help/npm and corrected:

- codex: --full-auto deprecated -> --sandbox workspace-write; --yolo -> --dangerously-bypass-approvals-and-sandbox (yolo kept as noted alias)
- claude-code: --effort levels low/medium/high/xhigh/max (dropped removed 'auto', added 'xhigh'); fixed stray table cell
- grok: --session-id is UUID-only for new sessions (cannot resume by name); rewrote the Session Continuation example; noted --max-turns now exists
- blackbox: wrong npm package (@blackboxai/cli is unrelated) -> @blackbox_ai/blackbox-cli; removed dead source-repo link and phantom session/info subcommands
This commit is contained in:
teknium1 2026-07-23 21:21:58 -07:00 • committed by Teknium
parent 1c646499b6
commit 9a894dae5f
4 changed files with 39 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

23
optional-skills/autonomous-ai-agents/blackbox/SKILL.md
View file

@ -1,7 +1,7 @@
---
name: blackbox
description: Delegate coding tasks to the Blackbox AI multi-model CLI.
version: 1.0.0
version: 1.0.1
author: Hermes Agent (Nous Research)
license: MIT
platforms: [linux, macos, windows]
@ -15,17 +15,12 @@ metadata:
Delegate coding tasks to [Blackbox AI](https://www.blackbox.ai/) via the Hermes terminal. Blackbox is a multi-model coding agent CLI that dispatches tasks to multiple LLMs (Claude, Codex, Gemini, Blackbox Pro) and uses a judge to select the best implementation.
The CLI is [open-source](https://github.com/blackboxaicode/cli) (GPL-3.0, TypeScript, forked from Gemini CLI) and supports interactive sessions, non-interactive one-shots, checkpointing, MCP, and vision model switching.
The CLI (npm `@blackbox_ai/blackbox-cli`, binary `blackbox`) is a TypeScript coding agent (forked from Gemini CLI) and supports interactive sessions, non-interactive one-shots, checkpointing, MCP, and vision model switching.
## Prerequisites
- Node.js 20+ installed
- Blackbox CLI installed: `npm install -g @blackboxai/cli`
- Or install from source:
```
git clone https://github.com/blackboxaicode/cli.git
cd cli && npm install && npm install -g .
```
- Blackbox CLI installed: `npm install -g @blackbox_ai/blackbox-cli` (binary: `blackbox`)
- API key from [app.blackbox.ai/dashboard](https://app.blackbox.ai/dashboard)
- Configured: run `blackbox configure` and enter your API key
- Use `pty=true` in terminal calls — Blackbox CLI is an interactive terminal app
@ -110,12 +105,16 @@ Blackbox's unique feature is running the same task through multiple models and j
| Flag | Effect |
|------|--------|
| `--prompt "task"` | Non-interactive one-shot execution |
| `--prompt "task"` (`-p`) | Non-interactive one-shot execution |
| `--resume-checkpoint "tag"` | Resume from a saved checkpoint |
| `--yolo` | Auto-approve all actions and model switches |
| `blackbox session` | Start interactive chat session |
| `--yolo` (`-y`) | Auto-approve all actions and model switches |
| `--vlm-switch-mode <mode>` | Image-handling: `once`, `session`, or `persist` |
| `-c, --checkpointing` | Enable checkpointing of file edits |
| `blackbox configure` | Change settings, providers, models |
| `blackbox info` | Display system information |
| `blackbox update` | Update the CLI to the latest version |
| `blackbox mcp` | Manage MCP servers |
| `blackbox extensions` | Manage CLI extensions |
| `blackbox voice <action>` / `blackbox shortcut` | Configure voice input / the `b` shortcut |
## Vision Support

25
optional-skills/autonomous-ai-agents/grok/SKILL.md
View file

@ -1,7 +1,7 @@
---
name: grok
description: "Delegate coding to xAI Grok Build CLI (features, PRs)."
version: 0.1.0
version: 0.1.1
author: Matt Maximo (MattMaximo), Hermes Agent
license: MIT
platforms: [linux, macos, windows]
@ -108,14 +108,16 @@ For pure automation, headless `-p` is still cleaner than the TUI.
|------|--------|
| `-p, --single <PROMPT>` | Send one prompt, run headless, exit |
| `-m, --model <MODEL>` | Choose a model |
| `-s, --session-id <ID>` | Create or resume a named headless session |
| `-r, --resume <ID>` | Resume an existing session |
| `-s, --session-id <UUID>` | Assign a **NEW** valid UUID to a fresh conversation (must not already exist). Does **not** resume — use `--resume`/`--continue` for that. Only valid with `--resume`/`--continue` when paired with `--fork-session` |
| `-r, --resume [<UUID>]` | Resume an existing session by its UUID (or the most recent if omitted) |
| `-c, --continue` | Continue the most recent session in the current directory |
| `--fork-session` | When resuming, create a new session ID instead of reusing the original |
| `--max-turns <N>` | Cap the maximum number of agent turns |
| `--cwd <PATH>` | Set the working directory |
| `--output-format <FMT>` | `plain` (default), `json`, or `streaming-json` |
| `--always-approve` | Auto-approve all tool executions (the `--full-auto` / `--yolo` equivalent) |
| `--no-alt-screen` | Run inline, no fullscreen TUI takeover |
| `--no-auto-update` | Skip background update checks (use in all automation) |
| `--no-auto-update` | Skip background update checks (use in all automation; hidden from `--help` but still works) |
### Output Formats
@ -151,14 +153,19 @@ with `tmux capture-pane`, exactly like the `claude-code` / `codex` skills.
### Session Continuation
Sessions are keyed by **UUID**, not by name. `--session-id` assigns a *new* UUID
to a fresh run (it does **not** resume); `--resume` takes an existing session's
UUID (or omit the value to resume the most recent).
```
# Start a named session
terminal(command="grok --no-auto-update -s refactor-db -p 'Start refactoring the database layer' --always-approve", workdir="/project", timeout=240)
# Start a session with a self-assigned UUID (must be a valid, unused UUID)
SID=$(uuidgen)
terminal(command="grok --no-auto-update -s $SID -p 'Start refactoring the database layer' --always-approve", workdir="/project", timeout=240)
# Resume it later
terminal(command="grok --no-auto-update -r refactor-db -p 'Now add connection pooling' --always-approve", workdir="/project", timeout=180)
# Resume that exact session later by its UUID
terminal(command="grok --no-auto-update -r $SID -p 'Now add connection pooling' --always-approve", workdir="/project", timeout=180)
# Or continue the most recent session in this directory
# Or just continue the most recent session in this directory (no UUID needed)
terminal(command="grok --no-auto-update -c -p 'What did you change last time?'", workdir="/project", timeout=60)
```

6
skills/autonomous-ai-agents/claude-code/SKILL.md
View file

@ -1,7 +1,7 @@
---
name: claude-code
description: "Delegate coding to Claude Code CLI (features, PRs)."
version: 2.2.0
version: 2.2.1
author: Hermes Agent + Teknium
license: MIT
platforms: [linux, macos, windows]
@ -265,7 +265,7 @@ Automatically falls back to the specified model when the default is overloaded (
| Flag | Effect |
|------|--------|
| `--model <alias>` | Model selection: `sonnet`, `opus`, `haiku`, or full name like `claude-sonnet-4-6` |
| `--effort <level>` | Reasoning depth: `low`, `medium`, `high`, `max`, `auto` | Both |
| `--effort <level>` | Reasoning depth: `low`, `medium`, `high`, `xhigh`, `max` |
| `--max-turns <n>` | Limit agentic loops (print mode only; prevents runaway) |
| `--max-budget-usd <n>` | Cap API spend in dollars (print mode only) |
| `--fallback-model <model>` | Auto-fallback when default model is overloaded (print mode only) |
@ -389,7 +389,7 @@ Use the `#` prefix in interactive mode to quickly add to memory: `# Always use 2
| Command | Purpose |
|---------|---------|
| `/model [model]` | Switch models mid-session (use arrow keys to adjust effort) |
| `/effort [level]` | Set reasoning effort: `low`, `medium`, `high`, `max`, or `auto` |
| `/effort [level]` | Set reasoning effort: `low`, `medium`, `high`, `xhigh`, or `max` |
| `/init` | Create a CLAUDE.md file for project memory |
| `/memory` | Open CLAUDE.md for editing |
| `/config` | Open interactive settings configuration |

16
skills/autonomous-ai-agents/codex/SKILL.md
View file

@ -1,7 +1,7 @@
---
name: codex
description: "Delegate coding to OpenAI Codex CLI (features, PRs)."
version: 1.0.0
version: 1.0.1
author: Hermes Agent
license: MIT
platforms: [linux, macos, windows]
@ -53,7 +53,7 @@ terminal(command="cd $(mktemp -d) && git init && codex exec 'Build a snake game
```
# Start in background with PTY
terminal(command="codex exec --full-auto 'Refactor the auth module'", workdir="~/project", background=true, pty=true)
terminal(command="codex exec --sandbox workspace-write 'Refactor the auth module'", workdir="~/project", background=true, pty=true)
# Returns session_id
# Monitor progress
@ -72,10 +72,12 @@ process(action="kill", session_id="<id>")
| Flag | Effect |
|------|--------|
| `exec "prompt"` | One-shot execution, exits when done |
| `--full-auto` | Sandboxed but auto-approves file changes in workspace |
| `--yolo` | No sandbox, no approvals (fastest, most dangerous) |
| `--sandbox workspace-write` (`-s`) | Sandboxed but auto-approves file changes in the workspace (the recommended auto-build mode) |
| `--dangerously-bypass-approvals-and-sandbox` | No sandbox, no approvals (fastest, most dangerous; `--yolo` still works as a hidden alias) |
| `--sandbox danger-full-access` | No Codex sandbox; useful when the host service context breaks bubblewrap |
> **Deprecated:** `--full-auto` still works but the live CLI warns to use `--sandbox workspace-write` instead.
## Hermes Gateway Caveat
When invoking the Codex CLI from a Hermes gateway/service context (for example,
@ -110,8 +112,8 @@ terminal(command="git worktree add -b fix/issue-78 /tmp/issue-78 main", workdir=
terminal(command="git worktree add -b fix/issue-99 /tmp/issue-99 main", workdir="~/project")
# Launch Codex in each
terminal(command="codex --yolo exec 'Fix issue #78: <description>. Commit when done.'", workdir="/tmp/issue-78", background=true, pty=true)
terminal(command="codex --yolo exec 'Fix issue #99: <description>. Commit when done.'", workdir="/tmp/issue-99", background=true, pty=true)
terminal(command="codex --sandbox workspace-write exec 'Fix issue #78: <description>. Commit when done.'", workdir="/tmp/issue-78", background=true, pty=true)
terminal(command="codex --sandbox workspace-write exec 'Fix issue #99: <description>. Commit when done.'", workdir="/tmp/issue-99", background=true, pty=true)
# Monitor
process(action="list")
@ -143,7 +145,7 @@ terminal(command="gh pr comment 86 --body '<review>'", workdir="~/project")
1. **Always use `pty=true`** — Codex is an interactive terminal app and hangs without a PTY
2. **Git repo required** — Codex won't run outside a git directory. Use `mktemp -d && git init` for scratch
3. **Use `exec` for one-shots** — `codex exec "prompt"` runs and exits cleanly
4. **`--full-auto` for building** — auto-approves changes within the sandbox
4. **`--sandbox workspace-write` for building** — auto-approves changes within the sandbox (`--full-auto` is deprecated for this)
5. **Background for long tasks** — use `background=true` and monitor with `process` tool
6. **Don't interfere** — monitor with `poll`/`log`, be patient with long-running tasks
7. **Parallel is fine** — run multiple Codex processes at once for batch work