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.
npx agentmods add agents/reviewtoolkits/cpython-security-toolkit/validation-coveragegit clone --depth 1 https://github.com/ReviewToolkits/cpython-security-toolkitWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00050 | $0.00527 |
| Opus 5 | $0.00025 | $0.00264 |
| Sonnet 5 | $0.00010 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
validation-coverage scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: Detects security-sensitive value types where some assignment paths validate input but others do not. Specializes in the incomplete-fix pattern. Invoke when scanning http.cookies, wsgiref, urllib, or webbrows The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- yesterday First seen · 41 lines · 50 tokens per session scan A 18dab5a4e6e1
validation-coverage is an agent published in the GitHub repository ReviewToolkits/cpython-security-toolkit (1 stars, last pushed 2d ago), with no licence file. It adds 50 tokens to every session and 527 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Diplomat Reviewer
Reviews Python code for unguarded AI agent tool calls — database writes, API calls, payments, emails, shell commands — that have no validation, rate limiting, or confirmation. Use this when reviewing agent code, after accepting Copilot suggestions, or before committing changes.
overview
How Serpentine's structured CLI output gives AI coding agents precise structural context before they read a single file.
claude-code
Install the Serpentine skill and wire structural orientation into every Claude Code session.
codex
Add Serpentine instructions to your Codex project context via AGENTS.md.
copilot
Add Serpentine instructions to your Copilot project context.
cursor
Install the Serpentine rule and wire structural orientation into every Cursor session.