Dossier — security grade SAFE, quality 60/100

Security audit verdict: SAFE · quality 60/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by rwliebs · Agent Tool · ★ 87

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is Dossier safe to install? View the security audit →

About Dossier

DOSSIER Out of the weeds. Back to crafting products. Dossier is an AI-native product building platform. It gives you a living map of your entire product — structured, visible, and agent-ready — so you can stay focused on the product vision while your agents build the details. You've learned to build with AI. Dossier is what comes next. The problem it solves The tools that got you here worked fine — until the project got real. Now you're juggling ten chat windows, losing track of what's done and what's broken, pasting context into every new prompt, and watching agents confidently build the wrong thing. The build is ballooning. Consistency is slipping. You're spending more time managing the process than shaping the product. This isn't a tool problem. It's a scale problem. And it's the natural inflection point Dossier is built for. How it works Dossier structures your product into a hierarchical map — Product → Workflow → Feature card — and attaches a rich context card to every piece. Workflows describe the user's perspective; feature cards describe how the software will work. Each card holds the facts, assumptions, and questions that matter for that feature.

agent-orchestrationagent-orchestratoragentic-workflowaiai-codingai-toolsclaude-codecontext-engineeringcontext-managementdeveloper-experience

Quick Facts

Stars87
Forks18
LanguageTypeScript
CategoryAgent Tool
Quality Score60.0397059481497/100
Open Issues23
Last Updated2026-07-15
Created2026-01-23
Platformsclaude-code, node
Est. Tokens~16k

Dossier alternative? Top 6 similar tools

Looking for a Dossier alternative? If you're comparing Dossier with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • autospec by ariel-frischer · ⭐ 144

    CLI for streamlined spec-driven development

  • shep by shep-ai · ⭐ 262

    Ship features 10x faster. Built In Auto: Memory, K8S Agent & Security (SDD+SDLC) . 😇

  • pm-claude-code-setup by aakashg · ⭐ 151

    Ready-to-use CLAUDE.md and starter skill for product managers using Claude Code.

  • jat by joewinke · ⭐ 251

    The World's First Agentic IDE. Visual dashboard: live sessions, task management, code editor, terminal. Epic S

  • vibe-annotations by RaphaelRegnier · ⭐ 175

    AI-powered annotations for localhost development. Create visual feedback on your apps and let AI coding agents

  • Nexus-skills by Haaaiawd · ⭐ 163

    AI-native codebase intelligence skills — generate persistent .nexus-map/ knowledge bases and instantly query f

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is Dossier?

Dossier is Visual planning and context control for shipping big apps with AI coding. Build from scratch or map existing repos. Dossier maps user workflows, sets agent context per feature, builds, tests and ships. It is categorized as a Agent Tool with 87 GitHub stars.

What programming language is Dossier written in?

Dossier is primarily written in TypeScript. It covers topics such as agent-orchestration, agent-orchestrator, agentic-workflow.

How do I install or use Dossier?

You can find installation instructions and usage details in the Dossier GitHub repository at github.com/rwliebs/Dossier. The project has 87 stars and 18 forks, indicating an active community.

What are the best alternatives to Dossier?

The top alternatives to Dossier on Agent Skills Hub include autospec, shep, pm-claude-code-setup. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools