agentmods.dev

publer-gateway

publer-gateway is a skill for Claude Code, Codex from dougm1966/publer-gateway-mcp. It costs 64 tokens per session (483 once invoked), scanned A, original, MIT.

A safety guide for using Publer Gateway MCP to manage Publer workspaces, accounts, project defaults, and prepared publishing actions. Publer is a service for managing social-media publishing.

In plain words
What is it for?
Listing Publer workspaces and accounts, selecting project defaults, routing projects to workspaces, and previewing scheduled posts.
Why use it?
It keeps API keys out of chat and files, separates workspace setup from live changes, and requires approval before write actions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

not rated 0repo 3mo ago A scan 64 tokens original MIT

Good fit Listing Publer workspaces and accounts, selecting project defaults, routing projects to workspaces, and previewing scheduled posts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dougm1966/publer-gateway-mcp/publer-gateway
View source ↗ dougm1966/publer-gateway-mcp
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.

Any agent
npx skills add dougm1966/publer-gateway-mcp --skill publer-gateway
Clone the repo
git clone --depth 1 https://github.com/dougm1966/publer-gateway-mcp

Made for: Claude Code, Codex.

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 publer-gateway

README.md
[![agentmods](https://agentmods.dev/badge/skills/dougm1966/publer-gateway-mcp/publer-gateway/github.svg)](https://agentmods.dev/skills/dougm1966/publer-gateway-mcp/publer-gateway)
Your own site
<a href="https://agentmods.dev/skills/dougm1966/publer-gateway-mcp/publer-gateway"><img src="https://agentmods.dev/badge/skills/dougm1966/publer-gateway-mcp/publer-gateway/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 publer-gateway

Your own site · 80×15
<a href="https://agentmods.dev/skills/dougm1966/publer-gateway-mcp/publer-gateway"><img src="https://agentmods.dev/badge/skills/dougm1966/publer-gateway-mcp/publer-gateway.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 483 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.
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 $0.00064 $0.00483
Opus 5.5 $0.00026 $0.00193
Sonnet 5.5 $0.00013 $0.00097
Haiku 4.5 $0.00006 $0.00048

Measured 2mo ago against content hash ae6eff777800, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

publer-gateway 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 2mo 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.

skills/publer-gateway/SKILL.md · 43 lines

What it actually says

Publer Gateway

Use this skill to operate the publer-gateway-mcp server safely.

Core Rules

  • Keep PUBLER_API_KEY in the local MCP environment or secret manager only.
  • Never ask the user to paste a Publer API key into chat.
  • Never write secrets to repo files, docs, logs, screenshots, or generated payload packets.
  • Prefer explicit workspaceId while setting up a project, then use publer_set_project_default.
  • Treat workspace IDs and account IDs as non-secret but private operational metadata; mask them in summaries unless exact IDs are needed.
  • Read tools may run directly.
  • Write-capable tools must preview first and require explicit approval before live calls.

Setup Workflow

  1. Call publer_list_workspaces.
  2. Ask the user which business/workspace to use if multiple plausible choices exist.
  3. Call publer_list_accounts with the selected workspace.
  4. Map platform/account targets to account IDs.
  5. Call publer_set_project_default with projectPath, workspaceId, and selected accountIds.
  6. Confirm the default with publer_get_project_default.

Safe Write Workflow

  1. Build a draft payload from user-approved content.
  2. Call publer_preview_schedule_post.
  3. Show the user the target workspace, accounts, schedule, media, and copy.
  4. Ask for explicit approval for that exact payload.
  5. Only after approval, call publer_schedule_post with dryRun: false and confirm: true.
  6. If Publer returns a job ID, call publer_get_job_status until completion or failure.

Error Handling

  • For missing workspace defaults, list workspaces/accounts and set a default rather than guessing.
  • For Publer API errors, summarize safe status and corrective action. Do not expose raw authorization headers or key-adjacent details.
  • For unsupported platforms, say the platform needs manual handling or a non-Publer workflow.
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. 2mo ago First seen · 43 lines · 64 tokens per session scan A ae6eff777800

Subscribe to this mod's changes

publer-gateway is a skill published in the GitHub repository dougm1966/publer-gateway-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 64 tokens to every session and 483 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 2026-08-31.

Marketing and SEO
Related

publer-gateway compared with skills from other repositories

publer-gateway next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
publer-gatewaydougm1966/publer-gateway-mcpSkill03mo agoMITA64Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code