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 Matthew0822 · Agent Tool · ★ 171
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ToolReplay safe to install? View the security audit →
ToolReplay ToolReplay audits a recorded transcript of an AI agent's tool calls and reports where the session was non-deterministic, redundant, or outside its declared permissions. Here is the tool working, right now, on the dirty sample that ships in this repository. The command is shown above its output, and the output is pasted verbatim from a run in this checkout: What just happened Those three header lines and two findings are the whole audit of a six-call session. Read them top to bottom. is the number of records parsed from . Parsing is strict, so a six here means six well-formed lines with indices 0 through 5 and nothing malformed. is the first index where a deterministic re-run would disagree with the record. The tool found that index 5 repeated an earlier call but carried a different recorded response, so that is the earliest point the session stops being reproducible. counts the audit results below the header. They are printed in a fixed order, sorted by index then by kind, so the same input always prints byte-ide
| Stars | 171 |
| Forks | 18 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 70.9650050819145/100 |
| Last Updated | 2026-09-14 |
| Created | 2026-09-14 |
| Platforms | cli, python |
| Est. Tokens | ~19k |
Looking for a ToolReplay alternative? If you're comparing ToolReplay 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.
A test runner for agentskills.io-style AI agent skills
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 comman
Context cleaning for Claude Code — prune bloated sessions, protect Agent Teams from context loss, auto-guard w
Agent traces you can run, not just read.
🐤 Less permission fatigue, more momentum. Dippy knows what’s safe to run and keeps Claude on track when plans
Async Python client for the Model Context Protocol with interactive CLI and reactive Web UI, connecting AI mod
Explore other popular agent tool tools:
ToolReplay is Audit AI agent tool-call transcripts: hash-chain sealing, deterministic replay, and scope overreach checks. Dependency-free Python CLI.. It is categorized as a Agent Tool with 171 GitHub stars.
ToolReplay is primarily written in Python. It covers topics such as ai-agents, audit, cli.
You can find installation instructions and usage details in the ToolReplay GitHub repository at github.com/Matthew0822/ToolReplay. The project has 171 stars and 18 forks, indicating an active community.
ToolReplay is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to ToolReplay on Agent Skills Hub include agent-skills-eval, roam-code, cozempic. 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: