Borrowing it
Nothing to install: this file belongs to greenmtnsun/GitEasy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/greenmtnsun/GitEasy/main/.claude/skills/mcp-b2b-publisher/SKILL.mdgit clone --depth 1 https://github.com/greenmtnsun/GitEasyWrote 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.
[](https://agentmods.dev/skills/greenmtnsun/giteasy/mcp-b2b-publisher)<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/mcp-b2b-publisher"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/mcp-b2b-publisher/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.
<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/mcp-b2b-publisher"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/mcp-b2b-publisher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00080 | $0.01509 |
| Opus 5.5 | $0.00032 | $0.00604 |
| Sonnet 5.5 | $0.00016 | $0.00302 |
| Haiku 4.5 | $0.00008 | $0.00151 |
Grade A, and why
mcp-b2b-publisher 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP B2B Publisher Compliance Skill
When invoked, load and enforce the full rule sets from:
C:\Sysadmin\Scripts\WikiEngine\.claude\MCP_B2B_PUBLISHER.md(10 DO rules)C:\Sysadmin\Scripts\WikiEngine\.claude\MCP_B2B_PUBLISHER_DONTS.md(10 DONT rules)
If those files are not in the active project, fall back to the embedded rules below.
Quick-reference enforcement (embedded)
HARD DO rules — stop and flag before producing output
| Rule | Requirement |
|---|---|
| 01 | Every tool has a pain_statement naming role + measurable cost |
| 02 | Description ≤60 words total; first sentence ≤25 words; no "helps", "enables", "leverages" |
| 03 | outputSchema fully typed; status: "success"|"partial"|"error"; error includes { code, message, retryable } |
| 04 | OAuth 2.1 / RFC 8707; no tokens in tool results; scopes per-tool |
| 05 | Each tool carries its own SemVer version field; MAJOR bump on breaking changes |
| 06 | Every invocation emits metering event with tenant_id, invocation_id, billable_units |
| 07 | GA requires marketplace listing with pain statement, pricing, auth, example I/O |
| 08 | X-RateLimit-* headers on every response; soft-limit warning at <20% remaining |
| 09 | Structured JSON logs with invocation_id correlation; no credentials or PII |
ADVISORY DO rule
| Rule | Requirement |
|---|---|
| 10 | Freemium tier sized to prove ROI; free responses include _meta: { tier, calls_remaining, upgrade_url } |
HARD DONT rules — stop and flag before producing output
| Rule | Anti-pattern |
|---|---|
| 01 | No god-tools with mode/action/type branching; one tool = one focused contract |
| 02 | Auth trust boundary decided and documented before GA; no "auth is phase 2" |
| 03 | Tool names follow verb_specificNoun; no get_data, process, execute, run |
| 04 | Destructive tools (write/delete/send/pay) require audit gate + action_id in response |
| 05 | No bare object parameters; no options/config/payload blobs; all properties typed inline |
| 07 | Common workflows complete in ≤2 tool calls; no mandatory cursor-then-fetch patterns |
| 08 | Errors use taxonomy prefixes: AUTH_, VALIDATION_, NOT_FOUND_, UPSTREAM_, INTERNAL_; retryable always present |
| 10 | Every tool tested by watching an actual agent use it before GA — unit tests alone are not sufficient |
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.
- today First seen · 121 lines · 80 tokens per session scan A 1bfc44c343ca
mcp-b2b-publisher is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 80 tokens to every session and 1,509 once invoked, about $0.0003 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 2026-11-18.
mcp-b2b-publisher compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-b2b-publishergreenmtnsun/GitEasy | Skill | 1 | yesterday | MPL-2.0 | A | 80 | Claude Code |
| fto-triageanthropics/claude-for-legal | Skill | 10k | 2d ago | Apache-2.0 | A | 81 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 10k | 2d ago | Apache-2.0 | A | 68 | Claude Code |
| specification-writingwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | today | MIT | A | 49 | Claude Code |
| regulatory-research-fallbackHKUDS/OpenSpace | Skill | 8.0k | 6d ago | MIT | A | 20 | Claude Code, Codex |
| terms-of-servicegenspark-ai/genoffice | Skill | 13k | today | Apache-2.0 | A | 32 | Claude Code, Codex |
| gesellschaft-und-vertretung-klaerenKlotzkette/claude-fuer-deutsches-recht | Skill | 1.9k | today | Apache-2.0 | A | 65 | Claude Code |