What is refresh-third-party-inventory?

A workflow for repairing a Dependabot pull request whose third-party license check is failing. Dependabot is a service that proposes updates to project dependencies and often cannot run the project's follow-up inventory script.

Use it when a Dependabot update needs refreshed third-party license and build-test inventory files before the pull request can pass its checks.

It runs the required inventory refresh, shows the changes, and pauses for confirmation before creating a signed commit or pushing it to the pull request branch.

How SolaceProducts/solace-broker-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to SolaceProducts/solace-broker-mcp. 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/SolaceProducts/solace-broker-mcp/main/.claude/skills/refresh-third-party-inventory/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/SolaceProducts/solace-broker-mcp

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/solaceproducts/solace-broker-mcp/refresh-third-party-inventory/github.svg)](https://agentmods.dev/skills/solaceproducts/solace-broker-mcp/refresh-third-party-inventory)

Your own site

<a href="https://agentmods.dev/skills/solaceproducts/solace-broker-mcp/refresh-third-party-inventory"><img src="https://agentmods.dev/badge/skills/solaceproducts/solace-broker-mcp/refresh-third-party-inventory/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/solaceproducts/solace-broker-mcp/refresh-third-party-inventory"><img src="https://agentmods.dev/badge/skills/solaceproducts/solace-broker-mcp/refresh-third-party-inventory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,942 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.

Model	Per session	Once invoked
Fable 5.1	$0.00100	$0.02942
Opus 5.5	$0.00040	$0.01177
Sonnet 5.5	$0.00020	$0.00588
Haiku 4.5	$0.00010	$0.00294

Measured 6d ago against content hash 43df15da5d8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

refresh-third-party-inventory 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 6d 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/refresh-third-party-inventory/SKILL.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refresh third-party inventory

Run make refresh-third-party-inventory (SOL-152956) against a Dependabot PR and land the result, with a human checkpoint before anything gets pushed. Invoked with /refresh-third-party-inventory <PR number or URL>.

Dependabot bumps Go modules and re-pins GitHub Action SHAs but cannot run post-update scripts, so its own PRs land with THIRD_PARTY_LICENSES.md / THIRD_PARTY_BUILD_TEST.md unmodified and Third-party licenses current red. A scheduled workflow in SolaceDev/dax (SOL-153374) fixes that once a day: at 11:30 UTC it runs make refresh-third-party-inventory on each red Dependabot PR and pushes the result, and it reports a PR it cannot fix in #dax on Slack. This skill is for the cases that can't wait for that run, or that the run could not fix: the same command, asked for in plain language instead of remembered and typed by hand.

The one checkpoint is the diff, before anything is written. This skill checks out a real PR branch and pushes a real commit to it — Step 5 always stops and shows the diff, and committing and pushing (Step 6) only happen after that's explicitly confirmed. One confirmation covers both, the same way /changelog never commits and /add-logs never applies without being shown first. There is no "just push it if it looks fine" mode.

When to use

A Dependabot PR is red on Third-party licenses current and needs the routine fix.
Someone points at a failing run of that check and asks for it to be fixed.
Not for a PR failing for any other reason — see Step 2.
Not for a fork pull request — see Step 3.

Usage

/refresh-third-party-inventory <PR number> — e.g. /refresh-third-party-inventory 321
/refresh-third-party-inventory <PR URL>
/refresh-third-party-inventory <failing run URL> — resolve to its PR first
No argument: ask which PR or run to target before doing anything else.

Precondition: gh auth status first. Every step below needs an authenticated gh.

Steps

Read the full file on GitHub · 190 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.

6d ago Changed · +2 lines 43df15da5d8a
9d ago Changed · +9 lines b93d936a520f
2mo ago First seen · 179 lines · 100 tokens per session scan A b38ce8dce3bf

Subscribe to this mod's changes

refresh-third-party-inventory is a skill published in the GitHub repository SolaceProducts/solace-broker-mcp (18 stars, last pushed yesterday), licensed Apache-2.0. It adds 100 tokens to every session and 2,942 once invoked, about $0.0004 per session on Opus 5.5. 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.

Legal and compliance ai-agents go mcp solace

refresh-third-party-inventory next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
refresh-third-party-inventorySolaceProducts/solace-broker-mcp	Skill	18	yesterday	Apache-2.0	A	100	Claude Code
company-lookupolgasafonova/nordic-registry-mcp-server	Skill	14	17d ago	Apache-2.0	A	41	Cursor
gdpr-data-handlingHarmeet10000/skills	Skill	7	6mo ago	MIT	A	45	Claude Code, Codex
fto-triageanthropics/claude-for-legal	Skill	9.9k	3d ago	Apache-2.0	A	81	Claude Code
legal-holdanthropics/claude-for-legal	Skill	9.9k	3d ago	Apache-2.0	A	68	Claude Code
specification-writingwanshuiyin/Auto-claude-code-research-in-sleep	Skill	19k	3d ago	MIT	A	49	Claude Code
terms-of-servicegenspark-ai/genoffice	Skill	12k	yesterday	Apache-2.0	A	32	Claude Code, Codex

solace-broker-mcp: Skill for Claude Code