What is create-policies?

A guide for creating and testing DashClaw guard policies, which set rules for what AI agents may do.

Use it to define YAML policies for risk limits, allowed action types, approval requirements, webhooks, and content checks, then run them in warning or blocking mode.

It helps replace informal trust with explicit checks, warnings, blocks, and human approvals for risky agent actions.

How ucsandman/DashClaw configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ucsandman/DashClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ucsandman/DashClaw/main/.claude/skills/dashclaw-agent/create-policies/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/ucsandman/DashClaw

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ucsandman/dashclaw/create-policies.svg)](https://agentmods.dev/skills/ucsandman/dashclaw/create-policies)

Your own site

<a href="https://agentmods.dev/skills/ucsandman/dashclaw/create-policies"><img src="https://agentmods.dev/badge/skills/ucsandman/dashclaw/create-policies.svg" alt="Measured on agentmods" height="20"></a>

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,339 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00015	$0.01339
Opus 5	$0.00008	$0.00669
Sonnet 5	$0.00003	$0.00268
Haiku 4.5	$0.00002	$0.00134

Measured 6d ago against content hash 7835331eb143, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

create-policies scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -H "x-api-key: $DASHCLAW_API_KEY" $DASHCLAW_BASE_URL/api/policies

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

create-policies — 100% identical, 0 lines differ

.claude/skills/dashclaw-agent/create-policies/SKILL.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Guard Policies

Help developers define, import, and test guard policies that control what agents can and cannot do.

Policy Types

Type	Purpose	Example
`risk_threshold`	Block/warn when risk score exceeds limit	Block actions with risk > 80
`action_type_restriction`	Allow/deny specific action types	Block `security` actions without approval
`approval_gate`	Require human approval for matching actions	Require approval for deploys
`webhook_check`	Call external endpoint for policy decision	Check Jira ticket status before deploy
`semantic_guardrail`	LLM-based content analysis	Block PII in action metadata

Guard Modes

off — No policy enforcement (development only)
warn — Log policy violations but allow execution
enforce — Block policy violations (production recommended)

Defining Policies in YAML

Risk Threshold Policy

name: high-risk-blocker
type: risk_threshold
mode: enforce
conditions:
  risk_score_min: 80
  reversible: false
action: block
reason: "Irreversible actions with risk >= 80 require manual execution"

Action Type Restriction

name: no-unattended-deploys
type: action_type_restriction
mode: enforce
conditions:
  action_types:
    - deploy
    - database
action: require_approval
reason: "Deploy and database actions require human approval"

Approval Gate

name: production-approval-gate
type: approval_gate
mode: enforce
conditions:
  systems_touched:
    - production
  risk_score_min: 50
action: require_approval
reason: "Production access with risk >= 50 requires approval"

Cost Ceiling

name: cost-ceiling
type: risk_threshold
mode: enforce
conditions:
  cost_estimate_max: 100.00
action: block
reason: "Actions exceeding $100 estimated cost are blocked"

Content Filter

name: no-secrets-in-metadata
type: semantic_guardrail
mode: enforce
conditions:
  scan_fields:
    - declared_goal
    - output_summary
  patterns:
    - "password"
    - "api_key"
    - "secret"
action: block
reason: "Sensitive data detected in action metadata"

Read the full file on GitHub · 225 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

6d ago First seen · 225 lines · 15 tokens per session scan A 7835331eb143

Subscribe to this mod's changes

create-policies is a skill published in the GitHub repository ucsandman/DashClaw (297 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 1,339 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Security agent-framework agent-governance agent-runtime ai-agents ai-infrastructure ai-ops

optimizer

Analyzes and automatically optimizes existing agents by improving system prompts and tool configuration.

inclusionAI/AWorld · 18 tokens

text2agent

Creates new agents from user requirements by generating Python implementation and mcpconfig.

inclusionAI/AWorld · 19 tokens

tiktok_download

Single-file TikTok/Douyin video download and traffic metrics via TikHub API using only httpx; optional persisted raw API JSON plus a stdlib post-processor emitting CSV and simplified JSON. Supports one URL or concurrent batch (max 10 workers). No dependency on any project codebase.

inclusionAI/AWorld · 63 tokens

app_evaluator

A professional skill for App Evaluation (evaluating app's performance with score) and App Improvement (giving professional suggestions for improving the app's performance).

inclusionAI/AWorld · 33 tokens

self_evolve

Use for framework-gated self-evolve workflows in AWorld: evolve skills, create trajectory-backed proposals, inspect self-evolve run artifacts, run aworld-cli optimize, or prepare verified apply decisions through aworld.selfevolve gates.

inclusionAI/AWorld · 51 tokens

ad_video_create

Create ad-ready product video from product images, with or without character/subject images. The workflow leverages AI-powered image composition, scene understanding, and video generation. Video prompts should follow commercial shot language—visual hooks, product presence, hero shots, detail showcase, function…

inclusionAI/AWorld · 64 tokens

DashClaw: Skill for Claude Code