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 qkal · Codex Skill · ★ 50
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Canny safe to install? View the security audit →
Canny A warden for AI coding agents. It hooks into Claude Code and Codex CLI, keeps a ledger of what the agent actually did, and will not let it finish on a claim. Done. Skipped tests — one-liner, no branch to break. That is Claude Code, verbatim, during this project's first live run. It had been asked to add a function, it wrote the file with a shell heredoc, ran nothing, and finished. No error. No warning. Nothing in could have stopped it, because a rules file only asks the model to remember, and nothing checks that it did. Canny is the hook that noticed. On the next run of the same prompt, the agent's "done" was refused with this message: Canny: math.js changed, bu
| Stars | 50 |
| Forks | 5 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 65.7863524210215/100 |
| Last Updated | 2026-09-22 |
| Created | 2026-09-11 |
| Platforms | claude-code, cli, codex, node |
| Est. Tokens | ~19k |
Looking for a Canny alternative? If you're comparing Canny with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.
An LLM council that reviews your coding agent's every move
Best Practices for Claude Code Configuration
Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask /
Reusable Agent Skills, plus integrations (statusline, provider usage, vision) that install into Codex, Claude
TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, ca
Explore other popular codex skill tools:
Canny is Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger, zero runtime dependencies.. It is categorized as a Codex Skill with 50 GitHub stars.
Canny is primarily written in TypeScript. It covers topics such as agent-hooks, ai-agents, claude-code.
You can find installation instructions and usage details in the Canny GitHub repository at github.com/qkal/Canny. The project has 50 stars and 5 forks, indicating an active community.
Canny is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to Canny on Agent Skills Hub include jev-review, sage, claude-code-settings. 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: