# Agentskill Config

> Stores and retrieves per-user, per-project preferences for AI skills via a unified JSON-backed CLI. Loaded by consumer skills that declare a '## Skill Config' section with keys to persist across invocations.

- **Type:** Skill
- **Install:** `agentstack add skill-navishachiku-agentskill-config-agentskill-config`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [navishachiku](https://agentstack.voostack.com/s/navishachiku)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [navishachiku](https://github.com/navishachiku)
- **Source:** https://github.com/navishachiku/agentskill-config

## Install

```sh
agentstack add skill-navishachiku-agentskill-config-agentskill-config
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# agentskill-config

## Storage

Two-layer JSON files with per-key override priority: `project` overrides `global`; within the same layer, `` overrides `_shared`.

| Scope     | Path                                       |
| --------- | ------------------------------------------ |
| `global`  | `~/.agents/skill_config.json`              |
| `project` | `/.agents/skill_config.json` |

`` is resolved via `git rev-parse --show-toplevel`. The `project` layer path should be gitignored — personal preferences are not for team version control.

`_shared` is a reserved top-level key used when multiple skills share the same conceptual preference. Read applies a 4-layer automatic fallback:

```
1. project..
2. project._shared.
3. global..
4. global._shared.
```

The first non-null value is used.

---

## CLI

> `` = the agentskill-config directory (resolved from the load path by the agent); `` = consumer skill name (e.g. `git-open-pr`) or `_shared`.

```bash
SC=/scripts/agentskill-config.js

# Read (auto-fallback; outputs empty string and exits 0 if not found)
value=$(node "$SC" read  )

# Write (writes to the corresponding file by scope; mkdir -p automatically; idempotent merge)
# When writing to _shared, the CLI prints an impact-scope warning to stderr — agent should confirm with user before proceeding
node "$SC" write   "" --scope 

# List
node "$SC" list             # list a specific skill / _shared
node "$SC" list                # list all

# Clean (SHOULD --dry-run first to preview)
node "$SC" clean  [--scope ] [--dry-run]
```

For full flag details, stdout format, and exit codes, see `references/api.md`.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [navishachiku](https://github.com/navishachiku)
- **Source:** [navishachiku/agentskill-config](https://github.com/navishachiku/agentskill-config)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-navishachiku-agentskill-config-agentskill-config
- Seller: https://agentstack.voostack.com/s/navishachiku
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.