# Config

> View, update, and reset persistent FM-Agent analysis defaults for scope, execution, graph backends, and knowledge references.

- **Type:** Skill
- **Install:** `agentstack add skill-fmagent-project-fm-agent-skill-config`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [fmagent-project](https://agentstack.voostack.com/s/fmagent-project)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [fmagent-project](https://github.com/fmagent-project)
- **Source:** https://github.com/fmagent-project/FM-Agent-Skill/tree/main/plugins/fm-agent-skill/skills/config

## Install

```sh
agentstack add skill-fmagent-project-fm-agent-skill-config
```

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

## About

# FM-Agent configuration

Configuration lives at `fm_agent_plugin/config.json` in the target repository.
It holds defaults for submodules, one-phase and isolation policy, concurrency,
granularity, retry count, lock TTL, the CodeGraph command and selected graph
backend, extra-edge reference, and Markdown knowledge references. It never
copies API keys or knowledge file contents.

Read [runtime-path.md](../../references/runtime-path.md) and resolve
`FM_AGENT_PLUGIN_ROOT` before invoking a script. This shared skill must work in
both Codex and Claude Code; never use `CLAUDE_SKILL_DIR`.

Use `config.py show`, `set`, or `reset`; for example:

```bash
 "$FM_AGENT_PLUGIN_ROOT/scripts/config.py" set --project "$PROJECT" --submodule src --concurrency 8 --granularity 40
```

Validate an extra-edge file or directory before saving or using it:

```bash
 "$FM_AGENT_PLUGIN_ROOT/scripts/call_graph_edges.py" "$EDGE_FILE"
```

Each run merges saved defaults with its explicit parameters, with explicit
parameters winning. The merged scope, policy settings, knowledge hashes, and
file-or-directory extra-edge content hash form the baseline fingerprint; a
change requires a full analysis. Read [configuration.md](../../references/configuration.md).

## Source & license

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

- **Author:** [fmagent-project](https://github.com/fmagent-project)
- **Source:** [fmagent-project/FM-Agent-Skill](https://github.com/fmagent-project/FM-Agent-Skill)
- **License:** Apache-2.0

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-fmagent-project-fm-agent-skill-config
- Seller: https://agentstack.voostack.com/s/fmagent-project
- 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%.
