# Plan Enforcer Config

> Use when changing Plan Enforcer settings --- switch enforcement tier, adjust reconciliation interval, set completion gate mode, or view current configuration

- **Type:** Skill
- **Install:** `agentstack add skill-jccidc-plan-enforcer-plan-enforcer-config`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [jccidc](https://agentstack.voostack.com/s/jccidc)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [jccidc](https://github.com/jccidc)
- **Source:** https://github.com/jccidc/.plan-enforcer/tree/main/skills/plan-enforcer-config
- **Website:** https://www.jccidc.com/

## Install

```sh
agentstack add skill-jccidc-plan-enforcer-plan-enforcer-config
```

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

## About

# Config

Read `.plan-enforcer/config.md`. If missing, create with defaults:

```yaml
---
tier: structural
reconcile_interval: 25
stale_threshold: 10
completion_gate: soft
ledger_path: .plan-enforcer/ledger.md
---
```

## Args

Parse from user message: `--tier`, `--reconcile-interval`, `--stale-threshold`, `--completion-gate`.

| Param              | Values                               | Default    |
|--------------------|--------------------------------------|------------|
| tier               | advisory, structural, enforced       | structural |
| reconcile_interval | tool-call count between sweeps       | 25         |
| stale_threshold    | tool-call count before stale warning | 10         |
| completion_gate    | soft (warn), hard (block completion) | soft       |

## Behavior

- Update only the values the user specified; leave the rest unchanged.
- If the installed CLI is available, prefer running `node ~/.claude/skills/plan-enforcer/src/config-cli.js .plan-enforcer/config.md ...` so the output matches the shared formatter exactly.
- If tier changes to/from **enforced**: explain that hooks will be installed/removed and ask user to confirm before writing.
- After any change, display the full current config.
- If no args provided: display current config, no changes.

## Source & license

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

- **Author:** [jccidc](https://github.com/jccidc)
- **Source:** [jccidc/.plan-enforcer](https://github.com/jccidc/.plan-enforcer)
- **License:** MIT
- **Homepage:** https://www.jccidc.com/

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-jccidc-plan-enforcer-plan-enforcer-config
- Seller: https://agentstack.voostack.com/s/jccidc
- 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%.