policy
Author MCP tool-call policy rules without hand-editing access.json
Best for MCP tool administratorsWorks with GitHubHigh risk
⌘source
- author
@jeremylongshore- language
- Python
★2.1kstars
281forks
May 1, 2026
✦overview.md
Key Features
- ·Author policy rules via chat commands
- ·Lint policy rules for correctness
- ·Add rules with effect, match, and options
- ·Remove existing rules by ID
- ·Complements hand-editing access.json
Use Cases
- →Add an auto-approve rule for a specific read tool call
- →Deny access to a tool based on path prefix
- →Require approval for sensitive tool calls
- →List all current policy rules to audit configuration
Best for
- ✓MCP tool administrators
- ✓access configuration
Not ideal for
- !ad-hoc one-off permissions
- !non-MCP environments
FAQs
name
policy
description
Author MCP tool-call policy rules without hand-editing access.json
license
MIT
version:1.0.0
author:Jeremy Longshore <jeremy@intentsolutions.io>
user-invocable:true
argument-hint:list | lint | add <id> <effect> <json-match> [--reason "..."] [--ttl-ms N] [--approvers N] [--priority N] | remove <id>
allowed-tools:["Read","Write","Edit","Bash(cmd:bun)","Bash(cmd:chmod)"]
/slack-channel:policy
Author, lint, and remove policy rules under access.json's top-level policy field.
The evaluator (evaluate() in policy.ts) is the veto layer for every MCP tool
call — this skill is the ergonomic front door to authoring rules without opening
access.json in a text editor.
See ACCESS.md §Policy schema for the full
rule shape and semantics. This skill does not replace the hand-edit path; it
complements it.
Usage
/slack-channel:policy list
/slack-channel:policy lint
/slack-channel:policy add <id> <effect> <json-match> [--reason "..."] [--ttl-ms N] [--approvers N] [--priority N]
/slack-channel:policy remove <id>
Effect is one of auto_approve, deny, require_approval.
json-match is a JSON object literal for the match field — e.g.
'{"tool":"read_file","pathPrefix":"/workspace/docs"}'. At least one field
must be populated; the validator rejects empty matches.
Options by effect
| Effect | Required | Optional |
|---|
$install
1-click copynpx skills add jeremylongshore/claude-code-plugins-plus-skills --skill policySafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
4/ 5
highMostly actionable with clear steps; only a few small gaps remain.