llm-cli-gateway: Skill for Claude Code

.claude/skills/supply-chain-guard/SKILL.md

supply-chain-guard is a skill for Claude Code from verivus-oss/llm-cli-gateway. It costs 139 tokens per session (1,999 once invoked), scanned A, original, MIT.

A release-checking process for tracking the exact production dependencies shipped by a project. It compares the current dependency set with a reviewed ledger and baseline, including packages brought in indirectly by other packages.

In plain words
What is it for?
Use it when a security audit or release gate runs, or when investigating dependency drift such as accepted upgrades, unknown packages, source anomalies, or integrity mismatches.
Why use it?
It catches unreviewed dependency changes that ordinary vulnerability scans may miss, including new transitive packages without known security reports.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex.

This is verivus-oss/llm-cli-gateway's own configuration. It tells Claude Code how to work on llm-cli-gateway itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llm-cli-gateway configures →

Part of the llm-gateway plugin — 24 skills, 4 commands, 2 MCP servers shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to verivus-oss/llm-cli-gateway. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/verivus-oss/llm-cli-gateway/main/.claude/skills/supply-chain-guard/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/verivus-oss/llm-cli-gateway

Made for: Claude Code.

Or install llm-gateway, the plugin that ships this one along with the rest of its 24 skills, 4 commands, 2 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for supply-chain-guard

README.md
[![agentmods](https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/supply-chain-guard/github.svg)](https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/supply-chain-guard)
Your own site
<a href="https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/supply-chain-guard"><img src="https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/supply-chain-guard/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for supply-chain-guard

Your own site · 80×15
<a href="https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/supply-chain-guard"><img src="https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/supply-chain-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,999 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00139 $0.01999
Opus 5 $0.00069 $0.01000
Sonnet 5 $0.00028 $0.00400
Haiku 4.5 $0.00014 $0.00200

Measured 10d ago against content hash da51b923c941, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

supply-chain-guard 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 10d ago.

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.

.claude/skills/supply-chain-guard/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/supply-chain-guard

Canonical process: docs/development/supply-chain-guard/RUNBOOK.md. Read it once at the start of any session that uses this skill; everything below is a condensed walkthrough and the runbook is the source of truth. Spec: docs/plans/supply-chain-guard.draft.md.

The problem this solves

The release gate is blocklist + invariants (npm audit, osv-scanner, the version blocklist, socket.yml) with no name/instance allowlist, so a new transitive package with no CVE enters the prod closure silently. This guard adds the allowlist layer: a committed ledger (supply-chain/prod-closure.ledger.json, per-name exact acceptedVersions) + instance baseline (prod-closure.baseline.json), and a scanner that fails the release when the shipped closure diverges from the reviewed baseline.

Not every drift is equal. A roll-forward (a ledgered name at a new accepted version) is low-risk but still blocks the exit-0 gate until the baseline is refreshed. A tag-along (a name not in the ledger, an unaccepted version, or a name absent from the baseline) needs a real review. Never rubber-stamp a tag-along.

When to invoke

  • npm run security:audit / CI failed with [supply-chain-guard] verdict exit 2|3.
  • You want to sweep drift before cutting a release.
  • You want to confirm no new package slipped into the prod tree.

Stages, and your responsibilities

1. Scan

npm run supply-chain:scan          # local/advisory (temp-copy fresh resolve; tolerates exit 2)
# or reproduce the gate exactly:
npm run supply-chain:scan:check    # --frozen, requires exit 0 (what CI runs)

Read report.md under .supply-chain/scan-<ts>/. Exit 0 clean, 2 roll-forward/dropped, 3 tag-along / source anomaly / integrity mismatch / reused-invariant failure (forbidden native-tar chain, blocked version, fetch-in-dist) / P2 license-violation (non-allowlisted or missing SPDX license) / P2 socket-policy-drift (a socket.yml issueRule changed from its reviewed value), 1 tool error. If clean, stop; otherwise triage every flagged row.

Read the full file on GitHub · 158 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. 10d ago First seen · 158 lines · 139 tokens per session scan A da51b923c941

Subscribe to this mod's changes

supply-chain-guard is a skill published in the GitHub repository verivus-oss/llm-cli-gateway (15 stars, last pushed yesterday), licensed MIT. It adds 139 tokens to every session and 1,999 once invoked, about $0.0007 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 2026-08-30.