build-dashclaw

build-dashclaw is a skill for Claude Code, Codex from ucsandman/DashClaw. It costs 24 tokens per session (1,383 once invoked), scanned A, original, MIT.

A development guide for DashClaw, an application that governs AI-agent actions through policies, approvals, records, and anomaly signals.

In plain words
What is it for?
Use it when adding DashClaw capabilities, changing its core API or extensions, writing tests, or updating continuous-integration checks.
Why use it?
It gives contributors the project’s architecture, required interfaces, technology choices, and testing expectations in one place.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/ucsandman/dashclaw/build-dashclaw
Any agent
npx skills add ucsandman/DashClaw --skill build-dashclaw
Clone the repo
git clone --depth 1 https://github.com/ucsandman/DashClaw

Made for: Claude Code, Codex.

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.

agentmods badge for build-dashclaw

README.md
[![agentmods](https://agentmods.dev/badge/skills/ucsandman/dashclaw/build-dashclaw.svg)](https://agentmods.dev/skills/ucsandman/dashclaw/build-dashclaw)
Your own site
<a href="https://agentmods.dev/skills/ucsandman/dashclaw/build-dashclaw"><img src="https://agentmods.dev/badge/skills/ucsandman/dashclaw/build-dashclaw.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,383 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.01383
Opus 5 $0.00012 $0.00691
Sonnet 5 $0.00005 $0.00277
Haiku 4.5 $0.00002 $0.00138

Measured 5d ago against content hash 97993db45368, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build-dashclaw scanned grade A with 0 findings 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 5d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/dashclaw-agent/build-dashclaw/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build DashClaw

Guide for contributing to the DashClaw codebase. Covers architecture, adding new capabilities, testing, and CI.

Architecture Overview

DashClaw is organized into 3 tiers:

Tier 1: Core Runtime (app/api/)

7 mandatory endpoints that define DashClaw's governance category:

Route Method Purpose
/api/guard POST Policy evaluation — "can I do this?"
/api/actions POST, PATCH, GET Action lifecycle recording
/api/approvals POST Human approval decisions
/api/assumptions POST, GET Reasoning integrity tracking
/api/signals GET Real-time anomaly detection
/api/policies GET, POST Guard policy management
/api/health GET System readiness

The 7-route boundary is CI-enforced. Adding a new core route requires justification.

Tier 2: Extensions (app/(extensions)/)

Modular operational intelligence:

  • Compliance, Drift, Evaluations, Scoring, Prompts, Webhooks, Learning

Tier 3: Archived (app/api/_archive/)

Legacy features from the "Agent Platform" era. Physically isolated.

Tech Stack

Layer Technology
Runtime Node.js 20+
Framework Next.js 16 (App Router)
Database Postgres (Neon recommended)
ORM Drizzle ORM
Auth NextAuth.js v4
UI React 18, Tailwind CSS 3
Testing Vitest + jsdom
Package Manager npm

Key Conventions

TEXT Primary Keys

All IDs are TEXT with crypto-random prefixed values:

import { randomBytes } from 'crypto';
const id = `act_${randomBytes(16).toString('hex')}`;

ID prefixes: ar_ (actions), oc_live_/oc_test_ (API keys), sp_ (scoring profiles), pt_ (prompt templates), etc.

Repository Pattern

No direct SQL in route handlers. All data access goes through repository modules:

app/lib/repositories/*.repository.js

Route handlers import from repositories, never inline SQL.

Auth Chain

Request → Strip client org headers → Rate limit → Route matching
  → Public routes: pass through
  → Protected routes: x-api-key (fast path: timing-safe compare)
    → Inject org context from resolved key

Read the full file on GitHub · 168 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.

  1. 5d ago First seen · 168 lines · 24 tokens per session scan A 97993db45368

Subscribe to this mod's changes

build-dashclaw is a skill published in the GitHub repository ucsandman/DashClaw (297 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 1,383 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories