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 instructions/ksegit/version-sentinel/copilot-instructionsgit clone --depth 1 https://github.com/KSEGIT/Version-SentinelWhat 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 | $0.00330 | $0.00330 |
| Opus 5 | $0.00165 | $0.00165 |
| Sonnet 5 | $0.00066 | $0.00066 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
Version-Sentinel copilot-instructions.md scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Version Sentinel
This workspace uses version-sentinel: dependency edits and install commands are blocked (via workspace hooks) until the target version is verified against its upstream registry and recorded.
When a tool call is BLOCKED with "version-sentinel"
- Look up the latest version of the package on its upstream registry:
- npm → npmjs.com
- pip / pyproject → pypi.org
- cargo → crates.io
- csproj → nuget.org
- Record the check by running in the terminal:
bash scripts/vs-record.sh <ecosystem> <pkg> <version> <source-url>The source must be anhttp(s)://URL you actually saw, orintentional: <reason>for deliberate pins. - Retry the original edit or install — the hook will see the fresh record and let it through.
Intentional pins
To deliberately install a non-latest version (CVE mitigation, compatibility), record with intentional: <reason> as the source. These show as intentional-pin, not DRIFT, in audits.
Audit
Run bash scripts/check-versions.sh before tagging a release. It scans package.json, requirements*.txt, constraints*.txt, pyproject.toml, Cargo.toml, *.csproj, *.fsproj, and *.vbproj and reports drift without blocking.
Escape hatch
Set VS_DISABLE=1 in the environment to disable blocking for a session (throwaway work only, with the user's awareness).
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 · 28 lines · 330 tokens per session scan A 8114742bd8b2
Version-Sentinel copilot-instructions.md is an instructions file published in the GitHub repository KSEGIT/Version-Sentinel (3 stars, last pushed 2d ago), licensed MIT. It adds 330 tokens to every session, about $0.0016 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
ai-dev-kit AGENTS.md
Instructions for noah-sheldon/ai-dev-kit, covering ai dev kit — agent instructions, core principles, contributor policy, available agents and agent orchestration.
magi-workflow CLAUDE.md
Instructions for howar31/magi-workflow, covering what this is, slash commands, subagents, project state model and project document tiers.
Cerebro AGENTS.md
Instructions for AgenticFirst/Cerebro, covering cerebro — agent context, read before touching integrations, project layout, conventions a fresh agent would otherwise miss and running locally.
discoclaw CLAUDE.md
Instructions for DiscoClaw/discoclaw, covering discoclaw, safety, context loading (strict), identity and workspace file ownership.
nextjs-skills CLAUDE.md
Instructions for mohamed-hossam1/nextjs-skills: All contribution rules — style, naming, file layout, verification — live in AGENTS.md. Read that first.
claude-plugins CLAUDE.md
Claude Code instructions for aiocean/claude-plugins, covering claude.md, what this is, plugin structure, marketplace registry and plugin categories.