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 infinri · Claude Skill · ★ 206
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Writ safe to install? View the security audit →
Writ A Claude Code harness that gives every coding session two helpers: a fast librarian that picks the rules that fit the current task, and a process keeper that blocks risky writes until you have approved a plan and tests. At the live 276-rule production corpus (post Phase 1-5 public-rulebook expansion), the librarian returns ranked results in 0.590 ms at the 95th percentile. At the 10,000-rule synthetic scale, it still holds at 0.557 ms while reducing context tokens by 726 times versus loading the whole rulebook every turn. See for the v1.2.0 release notes (proactive context-window management, hook hot-path latency consolidation, friction-log mode canonicalization, PostToolUse banner fix) and the v1.0.0 + v1.0.1 + v1.1.0 history of capabilities shipped. Browse the architecture in your browser Four self-contained HTML pages render the whole system. No clone or install required: open any link below and walk the diagrams. A sticky top nav inside each page cross-links to the other three, so you can flip between layers without coming back to the README.
| Stars | 206 |
| Forks | 14 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 70.9040071043056/100 |
| Last Updated | 2026-09-30 |
| Created | 2026-03-16 |
| Platforms | claude-code, python |
| Est. Tokens | ~20k |
These tools work well together with Writ for enhanced workflows:
Looking for a Writ alternative? If you're comparing Writ with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Remote approvals, policy checks, and execution evidence for unattended AI agents.
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 comman
Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in o
A Claude Code skill that 10x's your effective context window by dispatching tasks to background AI workers.
An always-on second brain you talk to. Voice notes in Telegram → typed, linked knowledge in your Obsidian vaul
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stabl
Explore other popular claude skill tools:
Writ is Governance runtime for Claude Code. Enforces workflow gates at tool time, delivers the engineering rules relevant to the work, and preserves decision provenance across sessions.. It is categorized as a Claude Skill with 206 GitHub stars.
Writ is primarily written in Python. It covers topics such as agent-governance, agent-tools, ai-agents.
You can find installation instructions and usage details in the Writ GitHub repository at github.com/infinri/Writ. The project has 206 stars and 14 forks, indicating an active community.
Writ is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to Writ on Agent Skills Hub include DashClaw, roam-code, octocode. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: