Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Ndx Config

ASecurity

View or change n-dx configuration with guided assistance

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsshellbashgitapi

Works with

claude codecliapimcp

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add en-dash-consulting/hotdogbenchmark --skill ndx-config --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ndx Config?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Ndx Config
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/en-dash-consulting-ndx-config/badge)](https://www.skillsdirectory.com/skills/en-dash-consulting-ndx-config)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: ndx-config
description: View or change n-dx configuration with guided assistance
argument-hint: "[key] [value]"
---

View or change n-dx configuration with guided assistance.

**Before anything else, note the current time in ISO-8601.** Use whatever your shell provides — `date -Iseconds` on POSIX shells, `Get-Date -Format o` in PowerShell. The record step at the end passes it as `--startedAt`, which is what stops this run from claiming every token the session spent before it began.

Available configuration areas:
- LLM settings: vendor (claude/codex), model, API keys, CLI paths
- Rex settings: budget thresholds, level-of-effort params, adapter
- Hench settings: provider, model, max turns, token budget, guard policies
- Web settings: dashboard port

If no arguments: show current configuration summary
If key only: show current value and explain what it controls
If key and value: validate and set the value

Run the appropriate `ndx config` command to apply changes.

## Final step — commit configuration changes

After applying any configuration change, commit the modified files:

1. Run `git status --porcelain` against the project root. This catches every dirty path — both direct file edits to `.n-dx.json`/`.rex/config.json`/`.hench/config.json` *and* MCP side-effect writes under `.rex/prd_tree/`. If the output is empty, print "Working tree clean — nothing to commit." and stop.
2. Run `git add -A` to stage all changes.
3. Commit with a message that names the key changed and includes the n-dx authorship + model audit trailer block . Build the message with your file-writing tool, never with shell quoting: heredocs and `$(...)` are POSIX-only and fail in PowerShell/cmd.exe (Git Bash is not part of Windows), and repeated `-m` flags insert blank lines that split the trailer block so git stops parsing it. Write exactly this message to a scratch file such as `.git/NDX_COMMIT_MSG`:

   ```
   ndx-config: update <key> configuration

   N-DX: skill/ndx-config
   Co-Authored-By: En Dash's n-dx <n-dx@endash.us>
   ```

   Then run `git commit -F .git/NDX_COMMIT_MSG` and delete the scratch file.

   Keep the `N-DX:` and `Co-Authored-By:` trailer lines exactly as shown — they form the audit trail used by downstream tooling.

## Record the run and its token cost

After committing, record this run so both the work and the tokens it spent are auditable alongside `ndx work` runs:

```sh
ndx hench record --task=<id> --status=completed --startedAt=<the time you noted>   --title="ndx-config: set <key>"   --summary="<one-line summary>"
```

Token usage is read automatically from this Claude Code session's transcript, counting only the spend since the previous record — so several skill runs in one session each get their own slice instead of all claiming the session total. Use `--task=skill:ndx-config`. A config change belongs to no PRD item, so it is recorded against a synthetic id that `get_token_usage` reports in its `orphans` bucket.

Skip this only if you changed nothing at all. If no transcript is found the record is still written with zero usage; the command reports which happened.

Attribution

en-dash-consultingen-dash-consulting
View sourceMore from en-dash-consulting →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →