Version-Sentinel CLAUDE.md

Project instructions for Version Sentinel, a Claude Code plugin that blocks dependency changes until a recent, source-cited version check is recorded. It supports several AI coding environments and package ecosystems.

In plain words
What is it for?
Use them when configuring, extending, or operating Version Sentinel across supported agents, hooks, commands, scripts, and dependency manifests.
Why use it?
They reduce the risk of using outdated, hallucinated, or compromised package versions by requiring evidence from the relevant package registry.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/ksegit/version-sentinel/claude-md
Clone the repo
git clone --depth 1 https://github.com/KSEGIT/Version-Sentinel
Per session 678 This file is loaded in full into every session.
When invoked 678 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00678 $0.00678
Opus 5 $0.00339 $0.00339
Sonnet 5 $0.00136 $0.00136
Haiku 4.5 $0.00068 $0.00068

Measured yesterday against content hash eb103fee873d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Version-Sentinel CLAUDE.md 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.

- `bash`, `jq`, `curl`, `python3` (3.11+) on PATH
CLAUDE.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Version Sentinel

Claude Code plugin that hard-blocks dependency additions, bumps, and downgrades until a fresh, source-cited version check is recorded. Multi-agent: ships adapters for Claude Code (also covers z.ai GLM Coding Plan / ZCode, which reuse the Claude Code plugin format), Kimi Code, GitHub Copilot (VS Code), Gemini CLI, OpenAI Codex, and Zed.

Project structure

.claude-plugin/       Plugin + marketplace metadata (plugin.json, marketplace.json)
plugin.json           Claude Code plugin manifest
hooks/hooks.json      Hook definitions, Claude Code/Codex schema (SessionStart, PreToolUse, PostToolUse)
hooks/gemini-hooks.json  Gemini CLI hook definitions (SessionStart startup, BeforeTool, AfterTool) — separate because Claude's plugin loader rejects Gemini keys in hooks/hooks.json; Gemini only auto-loads hooks/hooks.json, so point/copy this file on Gemini install (upstream: google-gemini/gemini-cli#25630)
scripts/              Bash scripts executed by hooks (prereq-check, detect-manifest-edit, detect-install-cmd, auto-record)
commands/             Slash commands: /vs-record, /check-versions (.md for Claude Code, .toml for Gemini CLI)
skills/               Skills: version-sentinel
agents/               Subagent: version-reviewer
kimi.plugin.json      Kimi Code plugin manifest
platforms/kimi/       Kimi Code adapter
gemini-extension.json Gemini CLI extension manifest
GEMINI.md             Gemini CLI auto-loaded context
.codex-plugin/        OpenAI Codex plugin metadata
.github/              GitHub Copilot hooks, agents, prompts
.agents/skills/       Cross-tool skills (Copilot, Zed, ...)
AGENTS.md             Cross-tool agent instructions
tests/                Test suite
bin/                  CLI entry points
docs/                 Documentation

Supported ecosystems

  • npmpackage.json via registry.npmjs.org
  • piprequirements*.txt, constraints*.txt, pyproject.toml via pypi.org
  • cargoCargo.toml via crates.io
  • dotnet*.csproj, *.fsproj, *.vbproj via api.nuget.org

Read the full file on GitHub · 53 lines

Changes

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.

  1. yesterday First seen · 53 lines · 678 tokens per session scan A eb103fee873d

Subscribe to this mod's changes

Version-Sentinel CLAUDE.md is an instructions file published in the GitHub repository KSEGIT/Version-Sentinel (3 stars, last pushed 2d ago), licensed MIT. It adds 678 tokens to every session, about $0.0034 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.